Background subtraction (BGS) is a fundamental task in computer vision with applications in video surveillance, object tracking, and recognition. Despite recent advancements, many deep learning-based BGS algorithms rely on large models to extract high-level representations, demanding significant computational resources and leading to inefficiencies in processing video streams. To address these limitations, we introduce the Sequential Feature Feedback Network (SeqFeedNet), a novel supervised algorithm for BGS in unseen videos that operates without additional preprocessing models. SeqFeedNet innovatively incorporates time-scale diverse sequential features and employs a feedback mechanism for each iteration. Moreover, we propose the Sequential Fit Training (SeqFiT) technique, enhancing model convergence during training. Evaluated on the CDNet 2014 dataset, SeqFeedNet not only achieves ∼ 5 times increase in inference speed but also outperforms F-Measure scores of the leading supervised algorithms, making it highly suitable for real-world applications. Our experiment demonstrates that SeqFeedNet surpasses state-of-the-art network without pre-trained segmentation model by 3.83% F-Measure on the CDnet 2014 dataset. Leading the way to establish a new benchmark for efficient and effective BGS in unseen videos. The code is released at https://github.com/tw-yshuang/SeqFeedNet.

Effective denoising is fundamental in image restoration, significantly impacting downstream computer vision tasks. Conventional CNN-based denoising models rely on paired training data of clean and noisy images, yet clean images are often unavailable in practical settings. Recent advancements in blind denoising, such as Noise2Void (N2V) and blind-spot networks, enable training without clean images; however, denoising quality remains an area for improvement. This paper introduces a novel Dense-in-Dense Network with Attention (DiDNA) designed specifically for blind denoising. By leveraging dense connections within a dense architecture and an attention module, DiDNA effectively captures complex noise patterns and enhances denoising capability. Experimental evaluations demonstrate that DiDNA not only surpasses existing blind denoising methods but also achieves competitive performance with traditional paired denoisers across CNN-based and non-CNN-based approaches.

The current halftone classification models use supervised learning, which requires a large dataset of labeled images. However, in practical situations, the source halftone type is often unknown, making it difficult to create such a dataset. These models are typically trained on synthetic halftone images and perform poorly on scanned halftone images. To address this issue, a new self-supervised learning (SSL) model has been proposed, based on Barlow Twins (BT) and Blue Noise (BN) dithering. In addition, an effective patch swapping augmentation technique has been developed to improve accuracy and speed up the training process. The pre-trained model is then fine-tuned using a modified progressive multi-granularity model with limited halftone labels. In overall, the proposed model outperforms existing halftone classification algorithms, becoming the state-of-the-art method.

Unsupervised image hashing is a widely used technique for large-scale image retrieval. This technique maps an image to a finite length of binary codes without extensive human-annotated data for compact storage and effective semantic retrieval. This study proposes a novel deep unsupervised double-bit hashing method for image retrieval. This approach is based on the double-bit hashing method, which has been shown to better preserve the neighboring structure of binary codes than single-bit hashing. Traditional double-bit hashing methods require the entire dataset to be processed simultaneously to determine optimal thresholding values of binary feature encoding. In contrast, the proposed method trains the hashing layer in a minibatch manner, allowing for adaptive threshold learning through a gradient-based optimization strategy. Additionally, unlike most former methods, which only train the hashing networks on top of fixed pre-trained neural networks backbone. The proposed learning framework trains both hashing and backbone networks alternately asynchronously. This strategy enables the model to maximize the learning capability of the hashing and backbone networks. Furthermore, adopting the lightweight Vision Transformer (ViT) in the proposed method allows the model to capture both local and global relationships between multiple image views exemplar, which lead to better generalization, thus maximizing the retrieval performance of the model. Extensive experiments on CIFAR10, NUS-WIDE, and FLICKR25K datasets validate that the proposed method has superior retrieval quality and computational efficiency than state-of-the-art methods.

Visual encryption and show through watermarking are widely used techniques to hide secret data in halftone images. The secret watermark can be quickly revealed when the halftone images are printed in transparency and overlaid on each other. The present studies emphasize developing a show-through watermarking technique for the clustered-dot halftone types. The proposed method exploits the properties of various configurations of dither array screens constructed using distinct Gaussian filters to embed watermarks. Two approaches are proposed, i.e., adjacent dither array pairs and the dither array translations. The optimal configuration of dither array parameters is developed to obtain maximum contrast and imperceptibility. Moreover, a new edge screen dithering is proposed to eliminate the edge artifacts, resulting in smooth screen transitions. As efficient ordered dithering is adopted for the watermark embedding, the joint watermarking and halftoning can be performed without additional computations. In comparison to the existing state-of-the-art show-through watermarking techniques, the proposed method can present superior image quality, computational simplicity, and decoded watermarks can be perceived with clear contrast when the images are overlaid with each other.

Human pose estimation is a fundamental yet challenging task in computer vision. However, difficult scenarios such as invisible keypoints, occlusions and small-scale persons are still not well-handed. In this paper, we present a novel pose estimation framework named UformPose which targets to relieve these issues. UformPose has two core designs: Shared Feature Pyramid Stem (SFPS) and U-shaped hierarchical Multi-scale Keypoint-aware Attention Module (U-MKAM). SFPS is a feature pyramid stem with shared mechanism to learn stronger low-level features at the initial stage, and the shared mechanism can facilitate cross-resolution commonality learning. Our U-MKAM attempts to generate high-quality high-resolution representations by integrating all levels of feature representation of the backbone layer by layer. More importantly, we utilize the flexibility of attention operations for keypoint-aware modeling, which explicitly captures and trades-offs the dependencies between keypoints. We empirically demonstrate the effectiveness of our framework through the competitive pose estimation results on the COCO dataset. Extensive experiments and visual analysis on CrowdPose demonstrate the robustness of our model in crowd scenes.

Road crack inspection is an important process to maintain the quality of roads for safety issues. The manual road inspection is laborious and time consuming. Thus, an automatic road crack detection is essential to make the inspection process easier and faster. Normally, this crack detection is conducted in real-time with low power computational devices and limited memory. Consequently, many former approaches adopted the patch-based approach to reduce computation for single forward, where the input image is divided into several non-overlapping patches. The generated patches are processed by independent CNN models to capture the crack position. Yet, this approach can lead to disintegrating issues because each patch is processed independently when the CNN fails to detect some patches of the crack. In this study, the improved patch-based crack detector is proposed, and the global patch analyzer is adopted to handle the above issue by considering the relation of each patch processing. Moreover, the proposed model also involves more features such as multiple decoder design and automatic resource mapper to yield superior results than that of the state-of-the-art methods in terms of the speed and accuracy as examined by extensive experiments.

Road crack is one of the prominent problems that can frequently occur in highways and main roads. The manual road crack evaluation is laborious, time-consuming, inaccurate, and it has several implementation issues. Conversely, the computer vision-based solution is very challenging due to the complex ambient conditions, including illumination, shadow, dust, and crack shape. Most of the cracks exist as irregular edge patterns and are the most important features for detection purpose. Recent advances in deep learning adopt a convolutional neural network as the base model to detect and localize crack with a single RGB image. Yet, this approach has an inaccurate boundary for crack localization, resulting in thicker and blurry edges. To overcome this problem, the study proposes a novel and robust road crack detection based on deep learning which also considers the original edge of the image as the additional feature. The main contribution of this work is adapting the original image gradient with the coarse crack detection result and refining it to produce more precise crack boundaries. Extensive experimental results have shown that the proposed method outperforms the former state-of-the-art methods in terms of the detection accuracy.

In many reversible data hiding (RDH) methods for halftone images, the traditional embedding process embeds a 1-bit secret message into each embeddable pixel or pattern. To improve the embedding efficiency and payload, we propose an RDH method used in halftone images based on the dynamic embedding states group (DESG), which can embed at least 1 bit of secret messages per embeddable pixel or pattern. First, by exploiting the statistical features of$4 \times 4$patterns and the state sequences in each image, the DESG is constructed dynamically, including$n$embedding states with their state patterns and state sequences. Then, secret messages are encoded by matching the longest common subsequence according to the DESG, which are split into several state sequences. The state sequences are embedded by Markov transitions between these$n$changing state patterns. Finally, reversibility is achieved by recording the DESG as the overhead information in RDH. Experiments show that the construction of DESG can improve the embedding efficiency under the same number of embeddable pixels or patterns, and the visual distortion is also significantly reduced by flipping fewer pixels.

The rapid development and growing of 4G and 5G mobile networks allow people all over the world to efficiently transmit and share data and information while bringing an increasing demand on information security. Data hiding is a general technique to embed secret messages to be protected in an imperceptible way into a cover media like an image, a video stream, or a document. Traditional data hiding intends to achieve high embedding capacity and imperceptibility of hidden secret messages for secure communication. However, it introduces permanent damage or distortion to the cover media when receiver extracts the secret messages from the cover media. To address this problem, reversible data hiding (RDH) was developed to allow the receiver completely extract the hidden secret messages while fully recovering the original cover media without any distortion. RDH has been widely used for many military and medical applications like the access authentication of reconnaissance images and the sharing of medical images in remote diagnosis. According to the format of cover media, RDH can be done in both plaintext and encryption domains. RDH in plaintext domain intends to embed the secret messages into the original cover media in a way that the marked media (the cover media with embedded secret messages) is visually the same as the original cover media and able to withstand the potential analysis. RDH in the encryption domain embeds the secret messages into the encrypted cover media (e.g., encrypted images) such that secret messages and cover media are protected in a high security level during transmission and completely reconstructed in the receiver side.

Facial expression recognition (FER) is an important and challenging problem for automatic inspection of surveillance videos. In recent years, with the progress of hardware and the evolution of deep learning technology, it is possible to change the way of tackling facial expression recognition. In this paper, we propose a sequence-based facial expression recognition framework for differentiating facial expression. The proposed framework is extended to a frame-to-sequence approach by exploiting temporal information with gated recurrent units. In addition, facial landmark points and facial action unit are also used as input features to train our network which can represent facial regions and its components effectively. Based on this, we build a robust facial expression system and is evaluated using two publicly available databases. The experimental results show that despite the uncontrolled factors in the videos, the proposed deep learning-based solution is consistent in achieving promising performance compared to that of the former schemes.

Image segmentation is one of the popular techniques for vision application, i.e., retrieving object information from an image. Segmentation not only provides the class and location of an object, but the associated contour as well. Recent advances of the segmentation deploy the encoder and decoder architectures with skip connection, and also utilize the edge information to obtain the best contour. This work focuses on maintaining the information flow from skip connection, and also identifies suited feature from the bottom layer. The feature selector can be also deployed in edge information for yielding segmentation contour. Designed filters are also employed to analyze the best feature for the reconstruction purpose. Experiment results show that the proposed scheme can improvise the performance of the simple ENet to achieve a superior IoU from 51.3% to 57.9%.

We propose an effective method to boost the accuracy of multi-person pose estimation in images. Initially, the three-layer fractal network was constructed to regress multi-person joints location heatmap that can help to enhance an image region with receptive field and capture more joints local-contextual feature information, thereby producing keypoints heatmap intermediate prediction to optimize human body joints regression results. Subsequently, the hierarchical bi-directional inference algorithm was proposed to calculate the degree of relatedness (call it Kinship) for adjacent joints, and it combines the Kinship between adjacent joints with the spatial constraints, which we refer to as joints kinship pattern matching mechanism, to determine the best matched joints pair. We iterate the above-mentioned joints matching process layer by layer until all joints are assigned to a corresponding individual. Comprehensive experiments demonstrate that the proposed approach outperforms the state-of-the-art schemes and achieves about 1% and 0.6% increase in mAP on MPII multi-person subset and MSCOCO 2016 keypoints challenge.

Normally, modeling 3D face is an effective way for pose-invariant recognition, yet its expensive computation significantly discourages potential applications. In this paper, a simple and fully automatic panoramic image-based pose-invariant face recognition method is proposed to present excellent accuracy with low complexity. In this paper, a face shape model with local morphing treatment is first constructed and considered as the alignment standard to deal with all of the possible geometric distortion problems. During the recognition phase, a proposed systematically designed algorithm with morphing and the selection function are both utilized to significantly ease the negative effects of various poses within ±45° in yaw and ±22.5° in pitch. As demonstrated in experimental results, a similar accuracy as that of the 3D start-of-the-arts is achieved with much less computational complexity.

A contrast enhancement method termed stratified parametric-oriented histogram equalization (SPOHE) is proposed to effectively provide a regional enhanced effect without visual artifacts, e.g., halo or blocking artifacts, which is normally incurred in the former simplified enhancement methods. First, the stratified sampling theory is applied to uniformly sample the original image through many divided strata with the size defined by the two parameters (α, β). Second, the required statistical information is efficiently derived through the integral image concept. Finally, the corrected SPOHE is also proposed to further improve the contrast with limited tradeoff computations. The experimental results demonstrate that the proposed scheme yields a cumulative distribution function similar to the actual one for an accurate contrast enhancement performance while significantly reducing the computational complexity. Moreover, compared with the former speed-oriented methods, good contrast and artifact-free results can be achieved simultaneously.

Degradation in visibility is often introduced to images captured in poor weather conditions, such as fog or haze. To overcome this problem, conventional approaches focus mainly on the enhancement of the overall image contrast. However, because of the unspecified light-source distribution or unsuitable mathematical constraints of the cost functions, it is often difficult to achieve quality results. In this paper, a fusion-based transmission estimation method is introduced to adaptively combine two different transmission models. Specifically, the new fusion weighting scheme and the atmospheric light computed from the Gaussian-based dark channel method improve the estimation of the locations of the light sources. To reduce the flickering effect introduced during the process of frame-based dehazing, a flicker-free module is formulated to alleviate the impacts. The systematic assessments show that this approach is capable of achieving superior defogging and dehazing performance, compared with superior defogging and dehazing performance, compared with the state-of-the-art methods, both quantitatively and qualitatively.

Ocular recognition is expected to provide a higher flexibility in handling practical applications as oppose to the iris recognition, which only works for the ideal open-eye case. However, the accuracy of the recent efforts is still far from satisfactory at uncontrollable conditions, such as eye blinking which implies any poses of eyes. To address these issues, the skin texture, eyelids, and additional geometrical features are employed. In addition, to achieve higher accuracy, sequential forward floating selection is utilized to select the best feature combinations. Finally, the non-linear support vector machine is applied for identification purpose. Experimental results demonstrate that the proposed algorithm achieves the best accuracy for both open eye and blinking eye scenarios. As a result, it offers greater flexibility for the prospective subjects during recognition as well as higher reliability for security.

This paper presents an effective image retrieval method by combining high-level features from convolutional neural network (CNN) model and low-level features from dot-diffused block truncation coding (DDBTC). The low-level features, e.g., texture and color, are constructed by vector quantization -indexed histogram from DDBTC bitmap, maximum, and minimum quantizers. Conversely, high-level features from CNN can effectively capture human perception. With the fusion of the DDBTC and CNN features, the extended deep learning two-layer codebook features is generated using the proposed two-layer codebook, dimension reduction, and similarity reweighting to improve the overall retrieval rate. Two metrics, average precision rate and average recall rate (ARR), are employed to examine various data sets. As documented in the experimental results, the proposed schemes can achieve superior performance compared with the state-of-the-art methods with either low-or high-level features in terms of the retrieval rate. Thus, it can be a strong candidate for various image retrieval related applications.

Recent studies on category relations have shown the promising progress in addressing classification problems. Existing works independently consider the known relation and classifier optimization, and thus restrain the room for performance improvement. In this work, a new loss function is proposed to leverage the underlining relations among categories and classifiers. In addition, the bipolar relation (BR) graph is employed to formulate a general form for diverse relations. This bipolar graph is automatically learnt for reliving the constraints which may happen during the cost minimization. Extensive experiments on three benchmarks with various hypotheses and graphs demonstrate that our method can offer a significant performance improvement by jointly learning from both BR graph and hypothesis, in particular on a small training dataset scenario that suffers from severe overfitting problem.

Block truncation coding (BTC) has been considered as a highly efficient compression technique for decades, but the blocking artifact is its main issue. The halftoning-based BTC has significantly eased this issue, yet an apparent impulse noise artifact is accompanied. In this study, an improved BTC, termed adaptive dot-diffused BTC (ADBTC), is proposed to further improve the visual quality. Also, this method provides an additional flexibility on the compression ratios determination in contrast to the former fixed and few number of configuration possibilities. As documented in the experimental results, the proposed method achieves the superior image quality regarding the five various objective IQA methods. As a result, it is a very competitive approach for the needs of both high frame rate and high-resolution image compression.

Facial landmark extraction system is crucial in various applications, including face recognition, expression analysis, face tracking, and face animation. This letter aims to improve the performance of an existing landmark extraction method proposed by Ren et al. in terms of error rate. Specifically, the Gaussian blur filter is applied on the input image to reduce noise interference and the theta-based split rule is deployed to strengthen the performance of the random forests. Then, global linear regression is applied instead of treating each landmark independently. Experimental results demonstrate that the proposed modified facial landmark extraction algorithm outperforms the conventional methods for both the LFPW and Helen databases.

Digital multitoning is an extension of halftoning for rendering more than two tones at each pixel for higher image quality. Although a lot of effort has been put in generating dispersed dots previously, the blue-noise feature can hardly be achieved for those printers utilizing the electrophotography (EP) process to avoid the physically unstable isolated dots. To overcome this issue, Chandu et al. proposed a screening method for yielding green-noise dot clusters, yet noisy multitone texture was accompanied. This degrades the visual quality and the stability of tone rendering. In this paper, a significantly improved homogeneity of clustered dots can be achieved by the proposed screening method based upon the new inter-iterative clustered-dot direct multi-bit search algorithm. Compared with the former approaches, the inter-iteration design leads to less error by the updated initial multitone patterns. As demonstrated in the experimental results, both of the high homogenous multitone texture and less noisy perception at all absorptance levels are offered in contrast to the former Chandu et al.'s results. The high-quality output proves it as a very competitive candidate for EP printers, e.g., laser printers.

Processing efficiency can be a key factor which dominates the value of a commercial product and its value-added application such as security. In this study, a computationally reduced halftoning-based watermarking is proposed. In encoder, the Efficient Direct Binary Search (EDBS) is employed to generate reference table to ensure the output is in halftone format. Subsequently, a number of optimized compressive tables with various texture angles are established for subsequent table lookup. In decoder, the Least-Mean-Square (LMS) enlarges the differences among those phenotypes of the embedded angles and the required number of dimensions for each angle. Finally, the naïve Bayes classifier is employed to collect the possibility information for classifying various angles. As documented in the experimental results, good image quality and correct detect rate can be obtained simultaneously. Moreover, a high processing efficiency of 0.6 milliseconds for an image of size 512×512 can also be achieved, which can substantially increase the commercial competitive strength in printing market, in particular the security issue is well addressed.

In this study, an improved Block Truncation Coding (BTC) image compression scheme, namely Near-Aperiodic Dot-Diffused BTC (NADDBTC), is described. Firstly, the existing regular structures for the generation of bitmap are completely modified for aperiodic compressed results. Moreover, an adaptive quantization levels selection strategy and two parameters Class Matrix (CM) and Diffused Matrix (DM) for image compression are developed and co-optimized. The improvements produce results of superior image quality. Furthermore, the adaptive quantization levels are introduced for balanced false contour, impulsive noise, and blocking artifact. Experimental results demonstrate that the proposed NADDBTC is capable of providing excellent image quality and visual perception, as well as processing efficiency, similar to DDBTC by exploiting the innate parallelism advantage of dot diffusion.

This paper presents a new approach to index color images using the features extracted from the error diffusion block truncation coding (EDBTC). The EDBTC produces two color quantizers and a bitmap image, which are further processed using vector quantization (VQ) to generate the image feature descriptor. Herein two features are introduced, namely, color histogram feature (CHF) and bit pattern histogram feature (BHF), to measure the similarity between a query image and the target image in database. The CHF and BHF are computed from the VQ-indexed color quantizer and VQ-indexed bitmap image, respectively. The distance computed from CHF and BHF can be utilized to measure the similarity between two images. As documented in the experimental result, the proposed indexing method outperforms the former block truncation coding based image indexing and the other existing image retrieval schemes with natural and textural data sets. Thus, the proposed EDBTC is not only examined with good capability for image compression but also offers an effective way to index images for the content-based image retrieval system.

Error diffusion is an efficient halftone method for mainly being applied on printers. The promising high image quality and processing efficiency endorse it as a popular and competitive candidate in halftoning and multitoning applications. The multitoning is an extension of halftoning, adopting more than two-tone levels for the improvement of the similarity between an original image and the converted image. Yet, the banding effect, indicating the areas with discontinuous tone level, disturbs the visual perception, and thus seriously degrades image quality. To solve the banding effect, the tone-replacement strategy is proposed in this paper. As documented in the experimental results, excellent tone-similarity as that of the original image and promising reconstructed dot-distribution can be provided simultaneously. Comparing with the former banding-free methods, the apparent improvements/features suggest that the proposed method can be a very competitive candidate for multitoning applications.

This paper presents a technique for content-based image retrieval (CBIR) by exploiting the advantage of low-complexity ordered-dither block truncation coding (ODBTC) for the generation of image content descriptor. In the encoding step, ODBTC compresses an image block into corresponding quantizers and bitmap image. Two image features are proposed to index an image, namely, color co-occurrence feature (CCF) and bit pattern features (BPF), which are generated directly from the ODBTC encoded data streams without performing the decoding process. The CCF and BPF of an image are simply derived from the two ODBTC quantizers and bitmap, respectively, by involving the visual codebook. Experimental results show that the proposed method is superior to the block truncation coding image retrieval systems and the other earlier methods, and thus prove that the ODBTC scheme is not only suited for image compression, because of its simplicity, but also offers a simple and effective descriptor to index images in CBIR system.

Compared with the error diffusion, dot diffusion provides an additional pixel-level parallelism for digital halftoning. However, even though its periodic and blocking artifacts had been eased by the previous works, it was still far from satisfactory in terms of the blue noise spectrum perspective. In this paper, we strengthen the relation among the pixel locations of the same processing order by an iterative halftoning method, and the results demonstrate a significant improvement. Moreover, a new approach of deriving the averaged power spectrum density is proposed to avoid the regular sampling of the well-known Bartlett's procedure which inaccurately presents the halftone periodicity of certain halftoning techniques with parallelism. As a result, the proposed dot diffusion is substantially superior to the state-of-the-art parallel halftoning methods in terms of visual quality and artifact-free property, and competitive runtime to the theoretical fastest ordered dithering is offered simultaneously.

This paper presents a new feature descriptor for vehicle verification. The object detection scheme generates the vehicle hypothesis (candidate) that requires subsequent confirmation in the vehicle verification stage with specific feature descriptors. In the procedure of vehicle verification, an image descriptor is generated from the statistical parameter of the curvelet-transformed (CT) subbands. The marginal distribution of CT output is a heavy-tailed bell-shaped function, which can be approximated as Gaussian, Laplace, and generalized Gaussian distribution (GGD) with high accuracy. The maximum likelihood estimation (MLE) produces the distribution parameters of each CT subband for the generation of the image feature descriptor. The classifier then assigns a class label for the vehicle hypothesis based on this descriptor information. As documented in the experimental results, this feature descriptor is effective and outperforms the existing methods in the vehicle verification tasks.

This paper presents a new approach to derive the image feature descriptor from the dot-diffused block truncation coding (DDBTC) compressed data stream. The image feature descriptor is simply constructed from two DDBTC representative color quantizers and its corresponding bitmap image. The color histogram feature (CHF) derived from two color quantizers represents the color distribution and image contrast, while the bit pattern feature (BPF) constructed from the bitmap image characterizes the image edges and textural information. The similarity between two images can be easily measured from their CHF and BPF values using a specific distance metric computation. Experimental results demonstrate the superiority of the proposed feature descriptor compared to the former existing schemes in image retrieval task under natural and textural images. The DDBTC method compresses an image efficiently, and at the same time, its corresponding compressed data stream can provide an effective feature descriptor for performing image retrieval and classification. Consequently, the proposed scheme can be considered as an effective candidate for real-time image retrieval applications.

Due to a variety of accidents, banknotes may be broken into several fragments. These fragments are usually stained, burned, partially lost, and twisted, which makes banknote reconstruction a hard problem. Since the fragments are always not intact, the traditional edge and texture based fragment assembling methods cannot be applied here. In this paper, we develop a framework for banknote reconstruction. We applied the techniques of SIFT point matching, RANSAC, and feature-based alignment. Moreover, convex quadratic optimization based on maximizing the reconstructed area and avoiding overlapping is adopted. Several simulations are given to demonstrate the effectiveness of our framework.

This letter presents a new method to derive the image feature descriptor for vehicle verification. The effectiveness of the proposed feature descriptor is based on the nature of the Gabor filter magnitude that tends to obey the Gamma distribution. The statistical parameters of the Gabor magnitude are computed using the Maximum Likelihood Estimation (MLE), which is later utilized to construct the feature descriptor. Conventionally, the Gabor magnitude is simply modeled by using Gaussian distribution, and thus the image descriptor consists of mean, standard deviation, and skewness values of the Gabor filter magnitude. However, recent investigations found that the skewness parameter is not contributing towards class separation. Based on our observation, the Gamma distribution provides a better statistical fitting to represent the Gabor filter magnitude when compared to the Gaussian distribution. As documented in the experimental results, the proposed feature descriptor yields higher accuracy for vehicle verification when compared to the conventional schemes.

Formerly, dimensionality reduction techniques are effective ways for extracting statistical significance of features from their original dimensions. However, the dimensionality reduction also induces an additional complexity burden which may encumber the real efficiency. In this paper, a technique is proposed for the reduction of the dimension of samples rather than the features in the former schemes, and it is able to additionally reduce the computational complexity of the applied systems during the reduction process. This method effectively reduces the redundancies of a sample, in particular for those objects which possess partially symmetric property, such as human face, pedestrian, and license plate. As demonstrated in the experiments, based upon the premises of faster speeds in training and detection by a factor of 4.06 and 1.24, respectively, similar accuracies to the ones without considering the proposed method are achieved. The performance verifies that the proposed technique can offer competitive practical values in pattern recognition related fields.

Block truncation coding (BTC) has been considered a highly efficient compression technique for decades. However, its inherent artifacts, blocking effect and false contour, caused by low bit rate configuration are the key problems. To deal with these, an improved BTC, namely dot-diffused BTC (DDBTC), is proposed in this paper. Moreover, this method can provide excellent processing efficiency by exploiting the nature parallelism advantage of the dot diffusion, and excellent image quality can also be offered through co-optimizing the class matrix and diffused matrix of the dot diffusion. According to the experimental results, the proposed DDBTC is superior to the former error-diffused BTC in terms of various objective image quality assessment methods as well as processing efficiency. In addition, the DDBTC also shows a significant image quality improvement comparing with that of the former ordered-dither BTC.

A prior work proposed by Chung-Wu considered an edge-based lookup table to obtain good inversed image quality, yet it suffers from some drawbacks in terms of image quality, memory consumption, and complexity. In this correspondence, an improved scheme is proposed to deal with these issues.

Conventionally, data embedding techniques aim at maintaining high-output image quality so that the difference between the original and the embedded images is imperceptible to the naked eye. Recently, as a new trend, some researchers exploited reversible data embedding techniques to deliberately degrade image quality to a desirable level of distortion. In this paper, a unified data embedding-scrambling technique called UES is proposed to achieve two objectives simultaneously, namely, high payload and adaptive scalable quality degradation. First, a pixel intensity value prediction method called checkerboard-based prediction is proposed to accurately predict 75% of the pixels in the image based on the information obtained from 25% of the image. Then, the locations of the predicted pixels are vacated to embed information while degrading the image quality. Given a desirable quality (quantified in SSIM) for the output image, UES guides the embedding-scrambling algorithm to handle the exact number of pixels, i.e., the perceptual quality of the embedded-scrambled image can be controlled. In addition, the prediction errors are stored at a predetermined precision using the structure side information to perfectly reconstruct or approximate the original image. In particular, given a desirable SSIM value, the precision of the stored prediction errors can be adjusted to control the perceptual quality of the reconstructed image. Experimental results confirmed that UES is able to perfectly reconstruct or approximate the original image with SSIM value > 0.99 after completely degrading its perceptual quality while embedding at 7.001 bpp on average.

In this study, a local contrast enhancement method, namely Parametric-Oriented Histogram Equalization (POHE), is proposed to effectively yield enhanced results. In general, the grayscale distribution of a specific region in an image can be modeled with a kernel function such as the Gaussian, and thus the corresponding estimated cumulative distribution function (cdf) can be considered as the transformation function for contrast enhancement. The required parameters, however, still need to access all of the pixels in the corresponding region, and thus consume a huge amount of computations. To cope with this, the concept of integral image is adopted to effectively derive the required parameters. In the experimental results, former well-known speed-oriented methods are adopted for comparison, and the results demonstrate that the proposed methods can provide high practical value for biometric and tracking/detection these active issues who desire high efficiency.

This paper presents a technique for Content-Based Image Retrieval (CBIR) by exploiting the low complexity advantage of the Ordered-Dither Block Truncation Coding (ODBTC) for generating image content descriptors. The two image features, namely Color Co-occurrence Feature (CCF) and Bit Pattern Features (BPF), are generated from ODBTC encoded data streams (without really performing an image compression or decoding process) to measure the similarity between two images. Experimental results show that the proposed method is superior to the Block Truncation Coding (BTC) image retrieval system and other former methods, and prove that the ODBTC scheme is not only suited for image compression for its simplicity, but also offers a conveniently way for image indexing in the content-based image retrieval system.

This paper presents a new face gender recognition scheme by enjoying the benefit from the dot diffusion among weak classifiers in recognition phase for a low resolution and non-aligned thumbnail image. The main problem of the former Adaboost approaches is that each weak classifier simply offers a binary decision, which fails to compensate the decision error by diffusing it to the rest weak classifiers. To cope with this, this work exploits the dot-diffused-based Adaboost to solve this problem. As documented in the experimental results, with the examination of Feret and CMU databases, this paper has shown that the proposed scheme is an effective candidate in improving the recognition accuracy rate and the efficiency of the overall system process for face gender recognition.

Moving object detection is an important and fundamental step for intelligent video surveillance systems because it provides a focus of attention for post-processing. A multilayer codebook-based background subtraction (MCBS) model is proposed for video sequences to detect moving objects. Combining the multilayer block-based strategy and the adaptive feature extraction from blocks of various sizes, the proposed method can remove most of the nonstationary (dynamic) background and significantly increase the processing efficiency. Moreover, the pixel-based classification is adopted for refining the results from the block-based background subtraction, which can further classify pixels as foreground, shadows, and highlights. As a result, the proposed scheme can provide a high precision and efficient processing speed to meet the requirements of real-time moving object detection.

Memory requirements (for storing intermediate signals) and critical path are essential issues for 2-D (or multidimensional) transforms. This paper presents new algorithms and hardware architectures to address the above issues in 2-D dual-mode (supporting 5/3 lossless and 9/7 lossy coding) lifting-based discrete wavelet transform (LDWT). The proposed 2-D dual-mode LDWT architecture has the merits of low transpose memory (TM), low latency, and regular signal flow, making it suitable for very large-scale integration implementation. The TM requirement of theN×N2-D 5/3 mode LDWT and 2-D 9/7 mode LDWT are 2Nand 4N, respectively. Comparison results indicate that the proposed hardware architecture has a lower lifting-based low TM size requirement than the previous architectures. As a result, it can be applied to real-time visual operations such as JPEG2000, motion-JPEG2000, MPEG-4 still texture object decoding, and wavelet-based scalable video coding applications.

Look-up table (LUT) halftoning is an efficient way to construct halftone images and approximately simulate the dot distribution of the learned halftone image set. In this paper, a general mechanism named multiple look-up table (MLUT) halftoning is proposed to generate the halftones of direct binary search (DBS), whereas the high efficient characteristic of the LUT is still preserved. In the MLUT, the standard deviation is adopted as an important feature to classify various tables. In addition, the proposed quick standard deviation evaluation is employed to yield an extremely low computational complexity in calculating the standard deviation. In the parameter optimization, the autocorrelation is adopted because it can fully characterize the periodicity of dot distribution. Experimental results demonstrate that the dot distribution generated by the proposed method approximates to that of the DBS, which enables the proposed scheme as a very competitive candidate in the copying and printing industry.

In this paper, a new class tiling designed dot diffusion along with the optimized class matrix and diffused matrix are proposed. The result of this method presents a nearly periodic-free halftone when compared to the former schemes. Formerly, the class matrix of the dot diffusion is duplicated and orthogonally tiled to fulfill the entire image for further thresholding and quantized-error diffusion, which accompanies subsequent periodic artifacts. In our observation, this artifact can be solved by manipulating the class tiling with comprising rotation, transpose, and alternatively shifting of the class matrices. As documented in the experimental results, the proposed dot diffusion has been compared with the former halftoning methods with parallelism in terms of image quality, processing efficiency, periodicity, and memory consumption; the proposed dot diffusion exhibits as a very competitive candidate in the printing/display market.

In this paper, a classified-based post-compensation algorithm for Color Filter Array (CFA) demosaicing is proposed. This technique can be used for improving the image quality of the interpolated results obtained by other CFA images. First, each pixel is classified according to its neighborhood texture variance and angle. Then, different Least-Mean-Square (LMS) filters are trained to adopt for dealing pixels of various characteristics. As documented in the experimental results, the proposed scheme can substantially boost the image quality; in addition, a better visual perceptual can be obtained. Notably, the proposed method can be considered as effective post-compensation by applying for any former schemes to yield an even better image quality.

In this paper, a halftoning-based watermarking scheme with high data capacity and image quality is presented. Three types of watermarks of various pixel-depths, including 1-bit, 2-bit, and 3-bit, are able to be embedded without prominently damaging the image quality. To achieve high marked image quality, the parallel-oriented high efficient Direct Binary Search (DBS) halftoning is adopted to cooperate with the proposed Orientation Modulation (OM) method. In the decoder, the Least-Mean-Square-trained (LMS-trained) filters are adopted to extract the features of marked images in the frequency domain, and the naïve Bayes classifier is employed to analyze the extracted features and further decode the watermark information. Experimental results demonstrate that the proposed DBS-based OM encoding scheme provides excellent image quality, high processing efficiency, and high robustness to adapt to practical printing application.

In this paper, the impact of the lips for facial recognition is investigated. In the first stage of the proposed system, a Fast Box Filtering (FBF) is proposed to generate a noise-free source with high processing efficiency. Afterward, five various mouth corners are detected though the proposed system, in which it is also able to resist beard and rotation problems. For the feature extraction, two geometric ratios and 10 parabolic related parameters are adopted for further recognition through the Support Vector Machine (SVM). Experimental results demonstrate that when the number of subjects is fewer or equal to 36, the Correct Accept Rate (CAR) is greater than 98%, and the False Accept Rate (FAR) is smaller than 0.064% (CAR>;95.6%, FAR<;0.083%| #Subjects ≤ 54). Moreover, the processing speed of the overall system achieves 34.43 fps (frame/sec) which meets the real-time requirement.

Look-Up Table (LUT) halftoning is an efficient way to construct halftone images, and approximately simulate the dot distribution of the learned halftone image set. In this study, a general mechanism named Multiple Look-Up Table (MLUT) halftoning is proposed to generate the halftones of Direct Binary Search (DBS), while the high efficient characteristic of the LUT is still preserved. In the MLUT, the standard deviation is adopted as an important feature to classify various tables. Moreover, the proposed Quick Standard Deviation Evaluation (QSDE) is employed to yield an extremely low computational complexity in calculating the standard deviation. In the parameter optimization, the autocorrelation is adopted since it can fully characterize the periodicity of dot distribution. Experimental results demonstrate that the visual quality of the proposed method can approximate to that of the DBS which is considered as the best halftoning in terms of image quality, which enable the proposed scheme as a very competitive candidate in coping printing industry.

In this study, the current state-of-the-art in moving objects segmentation for intelligent video surveillance has been surveyed. An efficient Modified Directional Lifting-based 9/7 Discrete Wavelet Transform (MDLDWT) structure is proposed to further reduce the computational cost and preserve the fine shape information in low resolution image. Although perfect moving object detection in a practical environment is a challenging task due to the vague object shape issues in the low resolution configuration, the experimental results document that the proposed low complexity MDLDWT scheme can provide more precise detection rate for multiple moving objects, and the fine shape information can be effectively preserved for the real-time video surveillance applications in both indoor and outdoor environments.

This paper presents an improved hand tracking system using pixel-based hierarchical-feature AdaBoosting (PBHFA), skin color segmentation, and codebook (CB) background cancelation. The proposed PBH feature significantly reduces the training time by a factor of at least 1440 compared to the traditional Haar-like feature. Moreover, lower computation and high tracking accuracy are also provided simultaneously. Yet, one of the disadvantages of the PBHFA is the false positive which is the consequence of the appearance of complex background in positive samples. To effectively reduce the false positive rate, the skin color segmentation and the foreground detection by applying the CB model are catered for rejecting all of the candidates which are not hand targets. As documented in the experimental results, the proposed system can achieve promising results, and thus it can be considered as an effective candidate in handling practical applications which require hand postures.

Block truncation coding (BTC) is an efficient compression technique with extremely low computational complexity. However, the blocking and false contour effects are two major deficiencies in BTC which cause severe perceptual artifacts. The former scheme, error-diffused BTC (EDBTC), can significantly improve the above issues through the visual low-pass compensation on the bitmap, which thus widens its possible application market, yet the corresponding security issue may limit its value. In this paper, a method namely complementary hiding EDBTC is developed to cope the above issue. This paper is managed by firstly discussing when a single watermark is embedded, and then multiple watermarks are employed to test the limitation of the proposed scheme. Herein, an adaptive external bias factor is employed to control the watermark embedding, and this factor also affects the image quality and robustness simultaneously. Experimental results demonstrate that the proposed method only requires an extremely small external bias factor to carry watermarks, which enables a high capacity scenario without significantly damaging image quality.

In this paper, a halftoning-based watermarking method is presented. This method enables high pixel-depth watermark embedding, while maintaining high image quality. This technique is capable of embedding watermarks with pixel depths up to 3 bits without causing prominent degradation to the image quality. To achieve high image quality, the parallel oriented high-efficient direct binary search (DBS) halftoning is selected to be integrated with the proposed orientation modulation (OM) method. The OM method utilizes different halftone texture orientations to carry different watermark data. In the decoder, the least-mean-square-trained filters are applied for feature extraction from watermarked images in the frequency domain, and the naïve Bayes classifier is used to analyze the extracted features and ultimately to decode the watermark data. Experimental results show that the DBS-based OM encoding method maintains a high degree of image quality and realizes the processing efficiency and robustness to be adapted in printing applications.

In this paper, the impact of the lips for identity recognition is investigated. In fact, it is a challenging issue for identity recognition solely by the lips. In the first stage of the proposed system, a fast box filtering is proposed to generate a noise-free source with high processing efficiency. Afterward, five various mouth corners are detected through the proposed system, in which it is also able to resist shadow, beard, and rotation problems. For the feature extraction, two geometric ratios and ten parabolic-related parameters are adopted for further recognition through the support vector machine. Experimental results demonstrate that, when the number of subjects is fewer or equal to 29, the correct accept rate (CAR) is greater than 98%, and the false accept rate (FAR) is smaller than 0.066%. (CAR > 95.02%, FAR < 0.095% # Subjects ≤ 57). Moreover, the processing speed of the overall system achieves 34.43 frames per second, which meets the real-time requirement. Thus, the proposed system can be an effective candidate for facial biometrics applications when other facial organs are covered or when it is applied for an access control system.

This paper presents an approach for personal identification using hand geometrical features, in which the infrared illumination device is employed to improve the usability of this hand recognition system. In the proposed system, prospective users can place their hands freely in front of the camera without any pegs or templates. The system can also work in normal environment, since no dark background is required. The idea behind the proposed system is to locate the tip of the middle finger and then rotate the palm image according to the tip point. Moreover, additional 12 important points are further identified and 30 features are defined from the information of those points. In addition, the Support Vector Machine (SVM) was used for distinguishing various hands. Experimental result shows an average Correct Identification Rate (CIR) of 98.75%, which is an encouraging consequence for a contact-free hand geometry identification system.

This study presents a hybrid hand tracking system using Pixel-Based Hierarchical-Feature AdaBoosting (PBHFA), skin color segmentation, and codebook background cancellation. The object of this approach is to construct a system which is able to cope with hand detection and further tracking tasks. To reduce the effect of false positive, the skin color segmentation and the foreground subtraction by applying the codebook model are employed for rejecting all of the candidates which are not hand targets. As documented in the experimental results, the proposed system can achieve promising results, and thus it can be considered as an effective candidate in handling practical applications which require hand postures.

The Adaboosting has attracted attention for its efficient face-detection performance. However, in the training process, the large number of possible Haar-like features in a standard sub-window becomes time consuming, which makes specific environment feature adaptation extremely difficult. This letter presents a two-stage hybrid face detection scheme using Probability-based Face Mask Pre-Filtering (PFMPF) and the Pixel-Based Hierarchical-Feature Adaboosting (PBHFA) method to effectively solve the above-mentioned problems in cascade Adaboosting. The two stages both provide far less training time than that of the cascade Adaboosting and thus reduce the computation complexity in face-detection tasks. In particular, the proposed PFMPF can effectively filter out more than 85% nonface in an image and the remaining few face candidates are then secondly filtered with a single PBHF Adaboost strong classifier. Given a${\rm M}\times{\rm N}$sub-window, the number of possible PBH features is simplified down to a level less than${\rm M}\times{\rm N}$, which significantly reduces the length of the training period by a factor of 1500. Moreover, when the two-stage hybrid face detection scheme are employed for practical face-detection tasks, the complexity is still lower than that of the integral-image based approach in the traditional Adaboosting method. Experimental results obtained using the gray feret database show that the proposed two-stage hybrid face detection scheme is significantly more effective than Haar-like features.

Block truncation coding (BTC) has been considered as an efficient compression technique for decades. However, the annoying blocking effect and false contour caused by low bit rate configuration are key problems. To solve these problems, many former halftoning-based BTCs are proposed. However, these schemes also induce another impulse noise issue while the previous issues still have room for improvement. To cope with this, the iteration-based halftoning is combined with BTC, namely Direct-Binary-Search BTC (DBSBTC) to solve the aforementioned problems. Moreover, the high-speed DBS halftoning method along with the block-based strategy yield even faster processing speed than some of the former halftoning-based BTC schemes. As documented in the experimental results, the proposed DBSBTC is superior to the former halftoning-base BTC schemes in terms of image quality, and which makes the former schemes as potential candidates for surveillance and computer vision applications.

This paper presents a hierarchical scheme with block-based and pixel-based codebooks for foreground detection. The codebook is mainly used to compress information to achieve a high efficient processing speed. In the block-based stage, 12 intensity values are employed to represent a block. The algorithm extends the concept of the block truncation coding, and thus it can further improve the processing efficiency by enjoying its low complexity advantage. In detail, the block-based stage can remove most of the backgrounds without reducing the true positive rate, yet it has low precision. To overcome this problem, the pixel-based stage is adopted to enhance the precision, which also can reduce the false positive rate. Moreover, the short-term information is employed to improve background updating for adaptive environments. As documented in the experimental results, the proposed algorithm can provide superior performance to that of the former related approaches.

For image-based data hiding, it is difficult to achieve good image quality when high embedding capacity and 100% data extraction are also demanded. In this study, the proposed method, namely, overall minimal-error searching (OMES) is developed to meet the aforementioned requirements. Moreover, the concept of secret sharing is also adopted to distribute watermarks into multiple halftone images, and the embedded information can only be extracted when all of the marked images are gathered. The OMES modifies the halftone values at the same position of all host images with the trained substitution table (S-Table). The S-Table makes the original combination of these halftone values as another meaningful combination for embedding watermark, which is the key part in determining the image quality. Thus, an optimization procedure is proposed to achieve the optimized S-Table. Two different encoders, called error-diffused-based and least-mean-square-based approaches are also developed to cooperate with the proposed OMES to cope with high processing speed and high image quality applications, respectively. Finally, for resisting the issues caused by the print-and-scan attack, such as zooming, rotation, and dot gain effect, a compensation correction procedure is also proposed. As demonstrated in the experimental results, the proposed approach provides good image quality, and is able to guard against some frequent happened attacks in printing applications.

This study proposes a method which can generate high quality inverse halftone images from halftone images. This method can be employed prior to any signal processing over a halftone image or the inverse halftoning used in JBIG2. The proposed method utilizes the least-mean-square (LMS) algorithm to establish a relationship between the current processing position and its corresponding neighboring positions in each type of halftone image, including direct binary search, error diffusion, dot diffusion, and ordered dithering. After which, a referenced region called a support region (SR) is used to extract features. The SR can be obtained by relabeling the LMS-trained filters with the order of importance. Moreover, the probability of black pixel occurrence is considered as a feature in this work. According to this feature, the probabilities of all possible grayscale values at the current processing position can be obtained by the Bayesian theorem. Consequently, the final output at this position is the grayscale value with the highest probability. Experimental results show that the proposed method offers better visual quality than that of Mese-Vaidyanathan's and Chang et al's methods in terms of human-visual peak signal-to-noise ratio (HPSNR). In addition, the memory consumption is also superior to Mese-Vaidyanathan's method.

Former research on inverse halftoning most focus on developing a general-purpose method for all types of halftone patterns, such as error diffusion, ordered dithering, etc., while fail to consider the natural discrepancies among various halftoning methods. To achieve optimal image quality for each halftoning method, the classification of halftone images is highly demanded. This study employed the least mean-square filter for improving the robustness of the extracted features, and employed the naive Bayes classifier to verify all the extracted features for classification. Nine of the most well-known halftoning methods were involved for testing. The experimental results demonstrated that the classification performance can achieve a 100% accuracy rate, and the number of distinguishable halftoning methods is more than that of a former method established by Chang and Yu.

In this paper, a low computational complexity method is proposed to embed a multi-tone visual pattern using the concept of secret sharing. One halftone image is obtained using regular error diffusion, and the other image is obtained using the proposed Generalized Noise-Balanced Error Diffusion (GNBEDF) in considering the properties of the watermark and the first halftone image in the same time. With the proposed method, the bi-level watermark embedding becomes a special case to this technology. The bi-level watermark decoding can be simply achieved via printing the two halftone images onto two transparencies and then superimposing them together to reveal the watermark pattern. However, as the multi-tone watermark is involved, the proposed Gaussian Difference (GD) approach is needed to perform the decoding to produce a decoded multi-tone watermark. Throughout this work, a lowpass filter obtained by Least-Mean-Square is employed to assess the image quality.

In this paper, the Pixel-Based Hierarchical-Feature Adaboosting (PBHFA) method is presented. The purpose of this approach is the reduction of computation complexity in face-detection tasks. The Adaboosting method has attracted attention for its efficient face-detection performance. However, in the training process, the large number of possible Haar-like features in a standard sub-window becomes time consuming, which makes specific environment feature adaptation extremely difficult. For this object, the PBHFA is proposed as a possible solution. Given a M × N sub-window, the number of possible PBH features is simplified down to a level less than M × N, which significantly reduces the length of the training period by a factor of 1500. Moreover, when the trained PBH features are employed for practical face-detection tasks, the hierarchically structural pattern matching also has lower complexity than that of the integral-image based approach in the traditional Adaboosting method. As documented in experimental results, with the MIT-CMU profile test set are examined, the proposed PBH features have shown significantly more effective than Haar-like features.

This study presents a new hierarchical scheme with coarse level and fine level for foreground detection using codebook model. The code book is mainly used to compress information to achieve high efficient processing speed. In the coarse level, six intensity values are employed to represent a block. The algorithm extends the concept of the Block Truncation Coding (BTC), and thus it can further improve processing efficiency. In detail, the coarse level is divided into two stages: Level one can increase processing speed and reduce noises without increasing False Positive (FP) rate; level two can increase detected precision of level one. Fine level can further enhance precision in coarse level. Moreover, this study also presents a new color model which can classify an input pixel as shadow, highlight, background, or foreground with the match function. This model can also cooperate with the Mixture of Gaussian (MOG) to remove shadow and thus enhances MOG's performance. As documented in the experimental results, the proposed algorithm can provide superior performance to that of the former Codebook (CB) approach.

This paper presents a cascaded scheme with block-based and pixel-based codebooks for background subtraction. The codebook is mainly used to compress information to achieve high efficient processing speed. In the block-based stage, 12 intensity values are employed to represent a block. The algorithm extends the concept of the Block Truncation Coding (BTC), and thus it can further improve the processing efficiency by enjoying its low complexity advantage. In detail, the block-based stage can remove the most noise without reducing the True Positive (TP) rate, yet it has low precision. To overcome this problem, the pixel-based stage is adopted to enhance the precision, which also can reduce the False Positive (FP) rate. Moreover, this study also presents a color model and a match function which can classify an input pixel as shadow, highlight, background, or foreground. As documented in the experimental results, the proposed algorithm can provide superior performance to that of the former approaches.

In this study, a low-complexity watermarking for embedding watermark into two or more halftone images with dot diffusion is proposed. The first halftone image is obtained by traditional dot diffusion, and the others are achieved by applying the proposed Secret-Shared Dot Diffusion technique (SSDDF). The visual decoding pattern can be observed when these similar dot-diffused images are printed on transparencies and then overlaid each other. Better decoded result can be obtained by computer-aid XNOR operation. Compared to the Dot Diffusion with Nonlinear Thresholding (DDNT) proposed by Taheri et al, the correct decoding rate can be improved with the proposed approach. Moreover, two extensions called dual SSDDF (DSSDDF) and Adaptive SSDDF (ASSDDF) are proposed to provide better decoding rates and compromised image quality.

Block Truncation Coding (BTC) has been considered as a highly efficient compression technique for decades. However, the annoying blocking effect and false contour under low bit rate configuration are its key problems. In this work, an improved BTC, namely Dot-Diffused BTC (DDBTC), is proposed to solve these problems. On one hand, the DDBTC can provide excellent processing efficiency by exploiting the innate parallelism advantage of dot diffusion. On the other hand, the DDBTC can provide excellent image quality by co-optimizing the class matrix and diffused matrix of the dot diffusion. The experimental results demonstrate that the proposed DDBTC is fully superior to the pervious Error-Diffused BTC (EDBTC) in terms of image quality and processing efficiency, and has much better image quality than that of the Ordered-Dither BTC (ODBTC).

Protecting privacy for exchanging information through the media has been a topic researched by many people. Up to now, cryptography has always had its ultimate role in protecting the secrecy between the sender and the intended receiver. However, nowadays steganography techniques are used increasingly besides cryptography to add more protective layer to the hidden data. In this letter, we show that the quality factor in a JPEG image can be an embedding space, and we discuss the ability of embedding a message to a JPEG image by managing JPEG quantization tables (QTs). In combination with some permutation algorithms, this scheme can be used as a tool for secret communication. The proposed method can achieve satisfactory decoded results with this straightforward JPEG double compression strategy.

Block Truncation Coding (BTC) is an efficient compression technique for its inherent simple coding strategy. However, the annoying blocking effect and false contour accompanied in high coding gain configurations make the applications relatively limited compares to some up-to-date compression schemes. For this, Error-Diffused Block Truncation Coding (EDBTC) is proposed to solve these problems and obtain satisfactory results. Unfortunately, the EDBTC sacrifices the parallel advantage of traditional BTC. Moreover, the number of diffused directions of EDBTC can be reduced to obtain higher efficiency. For these, the Interlaced Error-Diffused Block Truncation Coding (IEDBTC) is proposed in this work to claim back the parallel advantage. In addition, the diffused elements are also reduced from four to two with the proposed optimization procedure while preserving the image quality.

This work presents a novel reversible data-hiding scheme that embeds secret data into a transformed image and achieves lossless reconstruction of vector quantization (VQ) indices. The VQ compressed image is modified by the side-matched VQ scheme to yield a transformed image. Distribution of the transformed image is employed to achieve high embedding capacity and a low bit rate. Moreover, three configurations, under-hiding, normal-hiding, and over-hiding schemes, are utilized to improve the proposed scheme further for various applications. Experimental results demonstrate that the proposed scheme significantly enhances the compression ratio and embedding capacity. Experimental results also show that the proposed scheme achieves the best performance among approaches in literature in terms of the compression ratio and embedding capacity.

In this paper, a watermarking scheme, called majority-parity-guided error-diffused block truncation coding (MPG-EDBTC), is proposed to achieve high image quality and embedding capacity. EDBTC exploits the error diffusion to effectively reduce blocking effect and false contour which inherently exhibit in traditional BTC. In addition, the coding efficiency is significantly improved by replacing high and low means evaluation with extreme values substitution. The proposed MPG-EDBTC embeds a watermark simultaneously during compression by evaluating the parity value in a predefined parity-check region (PCR). As documented in the experimental results, the proposed scheme can provide good robustness, image quality, and processing efficiency. Finally, the proposed MPG-EDBTC is extended to embed multiple watermarks and achieves excellent image quality, robustness, and capacity. Nowadays, most multimedia is compressed before it is stored. It is more appropriate to embed information such as watermarks during compression. The proposed method has been proved to solve effectively the inherent problems in traditional BTC, and provide excellent performance in watermark embedding.

This study presents two predicted-based watermarking schemes, namely ahead AC-predicted watermarking (AAPW) and post AC-predicted watermarking (PAPW), by embedding information into low frequency AC coefficients of discrete cosine transform (DCT). The proposed methods utilize the DC values of the neighboring blocks to predict the AC coefficients of the center block. The low frequency AC coefficients are modified to carry watermark information. The least mean squares (LMS) is employed to yield the intermediate filters for cooperating with the neighboring DC coefficients to predict the original AC coefficients. During the LMS filter training, the training blocks are classified into different categories according to their texture angles and variances. The classified trained filter sets are then used to predict the AC coefficients even more precisely. As documented in the experimental results, the image quality and the embedded capacity of the proposed schemes are superior to former methods in the literature. Moreover, many attacks are addressed to show the robustness of the proposed methods.

In this paper, a watermarking scheme, called Majority-Parity-Guided Error-Diffused Block Truncation Coding (MPG-EDBTC), is proposed to achieve with high image quality and embedded capacity. The main problem of traditional BTC is its poor quality over configurations of high compression ratio. To overcome such problem, the extreme pixel values are employed to substitute both high and low means. The quantized error is also compensated by adjusting the neighboring pixels. With these strategies, the image quality and processing efficiency are improved. Moreover, the watermark is embedded by evaluating the parity value in a pre-defined Parity-Check Region (PCR). As seen in the experimental results, the proposed scheme can provide good robustness, image quality, and processing efficiency. Finally, the proposed MPG-EDBTC is extended to embed multiple watermarks and achieves excellent image quality, robustness, and capacity as well. Nowadays, most multimedia is stored in compressed format. It is more appropriate to embed information such as watermarks in compressed domain. The proposed method has been proved to solve effectively the inherent problems in traditional BTC, and provide excellent performance in watermark embedding.

This study presents a reasonable computational complexity watermarking algorithm to embed hidden pattern into two or more halftone images with adaptive noise-balanced error diffusion (ANBEDF). One halftone image is obtained by traditional error diffusion, and the others are obtained by ANBEDF. The visual decoded hidden pattern can be detected when the similar error-diffused images are overlaid each other. Better decoded result can be obtained by a simple XNOR operation. The proposed method employs the trained quality-noise look up Table (QNLUT) and the optimized multipliers to control the adaptive noise strength according to the local variance value. The experimental results show that higher decoding rate is available under the same image quality performance as former approaches reported in the literature.

Inverse halftoning is a key technology to yield a continuous tone image from a halftone image. The main application is to make some image enhancement or further compression of halftones more feasible. Many former approaches have been proposed in the literature. Among these, a recent method proposed by Chung and Wu using edge-based lookup table achieves good image quality, where the edge feature is adopted to refine the trained look-up table (LUT). However, it has three deficiencies, including 1) the edge features are limited in some predefined cases, which cannot full represent every potential possibility, 2) the lookup table grows exponentially when extreme grayscales are attempted to be recorded, and 3) the trained lookup table cannot fully include all the cases, which leaves some halftone patterns in practice have no associated output grayscale. Chang et al.'s method employed one trained filter to compensate the halftone patterns that are not recorded in LUT. However, one filter cannot fully characterize the full textures in an image. In this study, the halftone patterns are classified according to its variance and then used to train the corresponding filter sets, which are then employed to provide higher prediction accuracy by inner product with the corresponding halftone patterns. As documented in the experimental results, the proposed inverse halftoning provides excellent performance in image quality and memory consumption than former approaches.

Nowadays, most multimedia is stored in compressed bit stream format to save the storage apace or transmission time. This study proposes a novel technique for embedding flexible amounts of data in the bitmap of the improved Ordered Dither Block Truncation Coding (ODBTC) image, where the ordered dithering is used to dither the quantized BTC image to avoid the annoying false contour and blocking effect inherently existed in BTC image. Moreover, the LUT strategy is also used to significantly reduce the complexity. The inverse halftoning and the second round of halftoning are employed as the key steps in locating the embedded information bits. Experimental results demonstrate that an objective good quality image with flexible capacity and reasonable complexity is obtained. Moreover, the correct decoding rate of 100% is maintained, and the original host ODBTC image can also be reconstructed in the decoder when needed, which significantly boosts the flexibility in image quality control.

Block Truncation Coding (BTC) is an efficient compression technique for its inherent simple coding strategy. However, the annoying blocking effect and false contour accompanied in high coding gain configurations make the applications relatively limited compares to some up-to-date compression schemes. For this, Error-Diffused Block Truncation Coding (EDBTC) is proposed to solve these problems and obtain satisfactory results. Unfortunately, the EDBTC sacrifices the parallel advantage of traditional BTC. Moreover, the number of diffused directions of EDBTC can be reduced to obtain higher efficiency. For these, the Interlaced Error-Diffused Block Truncation Coding (IEDBTC) is proposed in this work to claim back the parallel advantage. In addition, the diffused elements are also reduced from four to two with the proposed optimization procedure while preserving the image quality.

In this work, a novel method based on Block Truncation Coding (BTC) and halftoning technique is proposed for embedding watermarks into compressed images. Block truncation coding is a simple and efficient image compression technique. However, it yields images of unacceptable quality and significant blocking effects are seen when the block size used increases. A modified technique known as Ordered Dither Block Truncation Coding (ODBTC) is proposed to solve the above problems while maintaining the same compression capability. In addition, ODBTC can also be used to embed a watermark into the compressed image. This technique incorporates void-and-cluster method with block truncation coding and ordered dithering to carry out watermarking. Experimental results have indicated that the resulting image quality is better and the algorithm less complex as than traditional block truncation coding. Many forms of attacks are also carried out and confirm the robustness of the proposed methods.

This work presents a fast algorithm, namely 2-D Symmetric Mask-based Discrete Wavelet Transform (SMDWT), to address some critical issues of the 2-D Discrete Wavelet Transform (DWT). Unlike the traditional DWT involving dependent decompositions, the SMDWT itself is subband processing independent, which can significantly reduce complexity. Moreover, DWT cannot directly obtain target subbands, which leads to an extra wasting in transpose memory, critical path, and operation time. These problems can be fully improved with the proposed SMDWT. Nowadays, many applications employ DWT as the core transformation approach, the problems indicated above have motivated researchers to develop fast algorithms for DWT. The proposed SMDWT has been proved as a highly efficient independent processing to yield target subbands which can be applied to real-time visual applications, such as moving object detection and tracking, texture segmentation, image/video compression, and any DWT-based applications.

Wavelet coding performs better than discrete cosine transform in visual processing. Moreover, it is scalable, which is important for modern video standards. The transpose memory requirement and operation speed are the two major concerns in 2-D lifting-based discrete wavelet transform (LDWT) implementation. This letter presents a novel algorithm, called 2-D symmetric mask-based discrete wavelet transform (SMDWT), to improve the critical issue of the 2-D LDWT, and then obtains the benefit of low-latency reduced complexity, and low transpose memory. The SMDWT also has the advantages of reduced complexity, regular signal coding, short critical path, reduced latency time, and independent subband coding processing. Furthermore, the 2-D LDWT performance can also be easily improved by exploiting an appropriate parallel method inherent to SMDWT. The proposed method has a significantly better lifting-based latency and complexity in 2-D DWT than normal 2-D 5/3 integer LDWT without degradation in image quality. The algorithm can be applied to real-time image/video applications.

Dot diffusion is an efficient approach which utilizes concepts of block-wise and parallel-oriented processing to generate halftones. However, the block-wise nature of processing reduces image quality much more significantly as compared to error diffusion. In this work, four types of filters with various sizes are employed in co-optimization procedures with class matrices of size 8 n 8 and 16 x 16 to improve the image quality. The optimal diffused weighting and area are determined through simulations. Many well-known halftoning methods, some of which includes direct binary search (DBS), error diffusion, ordered dithering, and prior dot diffusion methods, are also included for comparisons. Experimental results show that the proposed dot diffusion achieved quality close to some forms of error diffusion, and additionally, superior to the well-known Jarvis and Stucki error diffusion and Mese's dot diffusion. Moreover, the inherent parallel processing advantage of dot diffusion is preserved, allowing us to reap higher executing efficiency than both DBS and error diffusion.

Block Truncation Coding (BTC) is an efficient technology for image compression. An improved BTC algorithm, namely Ordered Dither Block Truncation Coding (ODBTC), is presented in this study. In order to provide better image quality, the void-and-cluster halftoning is combined with the BTC. The ODBTC results show that the image quality is improved when it is operated in high coding gain applications. Another feature of the ODBTC is the dither array Look Up Table (LUT), which significantly reduces the complexity compared to the BTC.

In this work, a high quality halftone image obtained by dot diffusion is proposed to reduce the deficiency gap with the error diffusion. Four kinds of filters with various sizes obtained by Least-Mean-Square (LMS) are also introduced to simulate the human visual system (HVS). These filters are employed in the optimization procedures for class matrix of size 8x8. According to numerous of simulations, an optimized diffused weighting is determined. Many well-known halftone methods, which include direct binary search (DBS), error diffusion, ordered dithering, and previous dot diffusion are also involved for comparisons. As demonstrated in the experiments, the quality of the proposed dot diffusion is close to some error diffusion and is even superior to the well-known Jarvis and Stucki error diffusion or Mese’s dot diffusion. Moreover, the dot diffusion inherently has the parallel processing advantage, which provides much higher executing efficiency than DBS or error diffusion.

In this paper, we present two novel robust methods for embedding watermarks into dithered halftone images. The first method is named Paired Subimage Matching Ordered Dithering (PSMOD), of which the decoder is provided with a priori information of the original watermark, and the corresponding application is copyright protection. The other method, Blind Paired Subimage Matching Ordered Dithering (BPSMOD), does not require the knowledge of the original watermark, and the main application is secret communication. Both methods utilize the bit and sub-subimage interleaving preprocesses. The experiments show that both techniques are sufficiently robust to guard against the cropping, tampering, and print-and-scan degradation processes, in either B/W or color dithered images. Both techniques are also sufficiently flexible for various levels of embedded capacities. Furthermore, a novel progressive coding scheme is also presented in this paper for the efficient display of dithered images. After the preprocessing of bit-interleaving, this algorithm utilizes the characteristic of reordered image to determine the transmitting order and then progressively reconstructs the dithered image. Moreover, the dithered images are further compressed by lossy and lossless procedures. The experimental results demonstrate high-quality reconstructions while maintaining low transmitted bit rates.

An improved data hiding in halftone images with cooperating pair toggling human visual system (PTHVS) is presented in this paper. An objective halftone image quality evaluation method based on the human visual system obtained by least-mean-square (LMS) is also introduced. By rigorously searching the optimum toggled pixels with the proposed human visual LMS-trained filter, the proposed method is proven to be superior to the data hiding smart pair toggling (DHSPT), proposed by Fu and Au, in image quality under a number of tested halftone images. The tested halftone images include ordered dithering, Floyd error diffusion, Jarvis error diffusion, and Stucki error diffusion images. Moreover, the proposed method offers high embedded capacity, and it is flexible to deal with different capacity applications.

A halftone watermarking method of high quality, robustness, and capacity flexibility is presented in this paper. An objective halftone image quality evaluation method based on the human visual system obtained by least-mean-square is also introduced. In the encoder, the kernels-alternated error diffusion (KAEDF) is applied. This scheme is able to maintain the computational complexity at the same level as an ordinary error diffusion. Compared with Hel-Or using ordered dithering, the proposed KAEDF yields a better image quality through using error diffusion. Moreover, the Haar wavelet transform (HWT) decoding is employed instead of lookup table (LUT), so as to reduce the computational complexity. As documented in the experimental results, this technique is able to guard against degradation due to tampering, cropping, rotation, as well as print-and-scan processes in error-diffused halftone images.

Block truncation coding is an efficient compression technique while offering good image quality. Nonetheless, the blocking effect inherent in BTC causes severe perceptual artifact in high compression ratio applications. In this paper, an error-diffused block truncation coding (EDBTC) is proposed to solve this problem. According to the EDBTC, the error caused by the difference between the original grayscale pixel value and the correspondingly high or low mean substitute is diffused to the predefined neighborhood, and hence the average grayscale will be maintained invariably. In addition, since the compressed data are widely distributed in the internet transmission, the extra message delivering in a secret way also highly raises attention recently. In this paper, we propose the compressed steganography using Hidden Referenced Halftoning (CSHRH), which cooperates with error diffusion and ordered dithering to achieve the objective of secret communication in BTC images. As documented in the experimental results, a low complexity with good image quality approach is obtained. Moreover, CSHRH is extended to secret-sharing steganography (SSS) and color extension steganography (CES). The SSS is able to distribute message into multiple host images and hence improves the security. The CES is able to deliver secure message via color embedded CSHRH image. Both extensions are also with an extra benefit of achieving high capacity message convection.

Wavelet coding has been shown to be better than discrete cosine transform (DCT) in image/video processing. Moreover, it has the feature of scalability, which is involved in modern video standards. This work presents novel algorithms, namely 2-D symmetric mask-based discrete wavelet transform (SMDWT), to improve the critical issue of the 2-D lifting-based discrete wavelet transform (LDWT), and then obtains the benefit of low latency, high-speed operation, and low temporal memory. The SMDWT also has the advantages of high-performance embedded periodic extension boundary treatment, reduced complexity, regular signal coding, short critical path, reduced latency time, and independent subband coding processing. Moreover, the 2-D lifting-based DWT performance can also be easily improved by exploiting appropriate parallel method inherently in SMDWT. Comparing with the normal 2-D 5/3 integer lifting-based DWT the proposed method significantly improves lifting-based latency and complexity in 2-D DWT without degradation in image quality. The algorithm can be applied to real-time image/video applications, such as JPEG2000, MPEG-4 still texture object decoding, and wavelet-based Scalable Video Coding (SVC).

This work employs the well known least-mean-square (LMS) method to design an adaptive filter to produce high-quality halftone images. The filter can be regarded as a transformation medium between original gray level images and corresponding halftone images. Experimental results indicate that the proposed LMS-designed halftoning offers the extra benefit of edge enhancement. Since a halftone image is typically used in printing, a modified printer model, which can coordinate with the proposed LMS-designed halftoning, is proposed to eliminate the harm caused by the dot-gain effect in printing. Moreover, two data hiding applications, the direct embedding LMS-designed halftone technique (DELDH) and the information sharing LMS-designed halftone technique (ISLDH), are proposed to demonstrate the performance of the proposed LMS-designed halftoning. The experimental results show that, both techniques can be used with the proposed modified printer model to achieve excellent image quality and decoded visual patterns

Generally speaking, the researches in model-based halftoning can be divided into error-diffusion based and iteration based methods. In this study, we propose a modified printer model to eliminate the damage from dot gain effect in printed halftone images. The proposed printer model cooperates with error diffusion and totally solves the dot gain problem in just one processing pass for all kinds of printed dot radii. Moreover, the modified printed image inherently needs fewer printed dots than the image obtained by traditional halftone method. With this modified printer model, it also offers an additional benefit of saving the cartridge expenditure. As documented in the experimental results, the average cartridge saving is around 38.58% with nature images.

A high efficiency and good quality error-diffused halftoning is proposed in this paper. An objective halftone image quality evaluation method based on human visual system obtained by least-mean-square is also introduced. The error diffusion algorithm, first introduced by Floyd and Steinberg in 1975, is currently the most popular method of digital halftoning. However, some annoying shortcomings, such as patches of regular textures, worm effect, and computational complexity still need to be improved. Ostromoukhov proposed a three-element error diffusion solving the problems described above, and achieved excellent performance. In this paper, we further reduced the complexity with the proposed two-element error diffusion by cooperating with the proposed LMS-trained quality evaluation. As demonstrated in experiments, the proposed technique further reduced the complexity by 33% compared to Ostromoukhov's method, and it is still comparable in image quality.

In this paper, a high-capacity data hiding is proposed for embedding a large amount of information into halftone images. The embedded watermark can be distributed into several error-diffused images with the proposed minimal-error bit-searching technique (MEBS). The method can also be generalized to self-decoding mode with dot diffusion or color halftone images. From the experiments, the embedded capacity from 33% up to 50% and good quality results are achieved. Furthermore, the proposed MEBS method is also extended for robust watermarking against the degradation from printing-and-scanning and several kinds of distortions. Finally, a least-mean square-based halftoning is developed to produce an edge-enhanced halftone image, and the technique also cooperates with MEBS for all the applications described above, including high-capacity data hiding with secret sharing or self-decoding mode, as well as robust watermarking. The results prove much sharper than the error diffusion or dot diffusion methods.

A halftone watermarking technique of high capacity, robustness, and capacity flexibility is presented in this paper. This parity-matched error diffusion (PMEDF) method is capable of achieving an embedded capacity as high as 6.25% to 25% with good image quality and without the original image as the reference to decode the watermark. As the experimental results demonstrated, this technique is able to guard against degradation due to cropping, tampering, and printed-and-scanned process in error-diffused halftone images.

A halftone watermarking method of high quality, robustness, and capacity flexibility is presented in this paper. An objective halftone image quality evaluation method based on the human visual system obtained by least-mean-square is also introduced. In the encoder, the kernels-alternated error diffusion (KAEDF) is applied. This is able to maintain the computational complexity at the same level as ordinary error diffusion. Compared with Hel-Or (2001) using ordered dithering, the proposed KAEDF yields a better image quality through using error diffusion. We also propose a weighted lookup table (WLUT) in the decoder instead of LUT, as proposed by Pei and Guo (2003), so as to achieve a higher decoded rate. As the experimental results demonstrated, this technique is able to guard against degradation due to tampering, cropping, rotation, as well as print-and-scan processes in error-diffused halftone images.

In this letter, we present a novel robust method for embedding watermarks into dithered halftone images. The method is named paired sub-image matching ordered dithering (PSMOD), of which the decoder is provided with a priori information of the original watermark. The method utilizes the bit and sub-subimage interleaving preprocesses. The experiments show that the technique is sufficiently robust to guard against the cropping, tampering, and printed-and-scanned degradation processes, in either B/W or color dithered images. This technique is also sufficiently flexible for various levels of embedded capacities.

In this paper, a high capacity data hiding is proposed for embedding a large amount of information into halftone images. The embedded watermark can be distributed into several error-diffused images by the proposed minimal error bit searching technique (MEBS). The method can be generalized to self-decoding mode with dot diffusion or color halftone images. From the experiments, the embedded capacity from 33% up to 50% and good quality result are achieved. Furthermore, the proposed MEBS method is also extended for robust watermarking to against the degradation from printing-and-scanning and several kinds of distortions.

In this letter, we propose a low-complexity algorithm for embedding watermarks into two or more error-diffused images. The first one is only a regular error-diffused image, and the others are achieved by applying the proposed noise-balanced error diffusion technique (NBEDF) to the original gray-level image. The visual decoding pattern can be perceived when these two or more similar error-diffused images are overlaid each other. Furthermore, with the proposed modified version of NBEDF, the two halftone images can be made from two totally different gray-tone images and still provide a clear and sharp visual decoding pattern.

A low computational complexity noise-balanced error diffusion (NBEDF) technique is proposed for embedding watermarks into error-diffused images. The visual decoding pattern can be perceived when two or more similar NBEDF images are overlaid, even in a high activity region. Also, with the modified improved version of NBEDF, two halftone images can be made from two totally different gray-tone images, and still provide a clear and sharp visual decoding pattern. With self-decoding techniques, we can also decode the pattern with only one NBEDF image. However, the NBEDF method is not so robust to damage due to printing or other distortions. Thus, a kernels-alternated error diffusion (KAEDF) technique is proposed. By using them alternately in the halftone process, we find that two well-known kernels (Jarvis, J.F. et al., 1976; Stucki, P., 1981) are compatible. In the decoder, because the spectral distributions of Jarvis and Stucki kernels are different in the 2D fast Fourier transform domain, we use the cumulative squared Euclidean distance criterion to determine each cell in a watermarked halftone image belonging to either Jarvis or Stucki, and then decode the watermark. Furthermore, because the detailed textures of Jarvis and Stucki patterns are somewhat different in the spatial domain, the lookup table (LUT) technique is also used for fast decoding. From simulation results, the correct decoding rates for both techniques are high and extremely robust, even after printing and scanning processes. Finally, we extend the hybrid NBEDF and KAEDF algorithms to two color EDF halftone images, where 8 independent KAEDF watermarks and 16 NBEDF watermarks can be inserted and still achieve a high-quality result.