Defocus blur, common in shallow depth-of-field photography, varies across image regions and is challenging to accurately estimate and restore. Existing deblurring methods often struggle to capture fine structural textures and do not effectively adapt to regional differences in blur. We propose Multi-Level Blur-Aware Stable Diffusion (MBSD), a novel framework that explicitly integrates regional blur recognition into a diffusion-based image restoration process. MBSD assigns blur-level labels to image patches using a Patch Blur Annotator (PBA), guiding a Multi-Scale Blur Estimator (MSBE) to predict soft blur probabilities and generate routing weights. These weights control a Blur-Adaptive Expert Mixer (BAEM), which adaptively combines features based on local blur severity. The features are then passed to a text-to-image diffusion model via a cross-attention mechanism, enabling region-specific restoration. Extensive experiments on public benchmarks demonstrate that MBSD delivers superior perceptual quality while maintaining competitive PSNR and SSIM, consistently outperforming state-of-the-art methods.

Gastrointestinal (GI) diseases if undiagnosed can lead to severe health complications, including malnutrition, dehydration, and even cancer. Colonoscopy, the gold standard for GI disorder diagnosis, often faces challenges such as low-contrast images due to poor illumination, making it difficult to detect fine details crucial for accurate diagnosis. Additionally, AI-based healthcare, including GI Disease Detection systems, is susceptible to adversarial attacks, raising significant concerns for patient safety due to potential misclassifications in clinical decision-making. To mitigate these issues, we introduce a novel Computer Assisted Diagnostics (CAD) system for GI disease detection and resilience against adversarial threats. Our approach incorporates two key innovations: first, a preprocessing technique using Quaternion Dark Channel Laplacian of Gaussian (QDC-LoG) for edge and contrast improvements; second, an ensemble of Convolutional Neural Networks (CNNs) and classifiers for robust GI disorder prediction. Through comprehensive experiments, we demonstrate that our method not only surpasses current state-of-the-art techniques, including advanced deep learning models and transformers, by achieving a 97.88% accuracy on the Wireless Capsule Endoscopy (WCE) Curated Colon Disease Dataset, but also shows exceptional specificities on Kvasir V1 and V2 datasets. Furthermore, our system exhibits strong resilience against Contrast Adversarial Degradation Attacks (CADA), ensuring reliable performance even under severe contrast reduction.

Gaze-based object manipulation intention inference is pivotal to natural and intuitive human-robot interaction. Existing methods confine spatial regularity to independent object selection and treat temporal regularity only as sequential order, thus spatio-temporal gaze regularities remain insufficiently exploited and lack a unified treatment. The objective of this study is to statistically analyze, model, and integrate gaze regularities within a unified probabilistic framework for inference. Accordingly, we propose a spatio-temporal gaze regularities guided dynamic fuzzy Bayesian network (DFBN) for intention inference. We statistically analyze the spatial gaze regularity as mutual exclusion and co-occurrence in joint object selection patterns, and the temporal regularity as duration-dependent attention with sequential dependencies. The regularities are modeled into probabilistic form, with spatio regularity modeled by autoregressive logistic regression and temporal regularity modeled by a Fuzzy Gaze-LSTM that fuses gaze duration with sequential order. These probabilistic models are fused into a likelihood modifier to generate interpretable posterior probabilities of intention, integrating a Bayesian network and sequential inference. Cross-dataset evaluations indicate stable and high performance. DFBN attains 96.47 1.75% accuracy and 96.41 1.85% F1 score, maintains accuracy on error sequences, and generalizes across younger and older groups, supporting robust intention inference. This study has the potential to inform other human-robot interaction assistance strategies by serving as intuitive gaze regularity cues.

This paper presents a novel image enhancement approach to avoid common artifacts such as over-exposure, color cast, and unnatural results. The key innovation lies in estimating the illumination map of an underexposed image using a sparse bright channel. Our approach includes an algorithm that enforces the sparsity of the inverted bright channel, enabling the indirect estimation of a coarse but suitable initial illumination map. This initial map is refined using an updated weight-constrained regularization with joint local exposure and detail feedback constraints, producing a piece-wise smooth, structure-preserving illumination map. Computer simulations show that the proposed method is competitive with or even outperforms several state-of-the-art enhancement methods in terms of both subjective and objective evaluations.

Tracheal intubation is a critical medical procedure involving the insertion of a tube into the trachea to maintain an open airway. While essential, this procedure carries significant risks, such as incorrect tube placement. Advances in visually guided intubation methods, like video laryngoscopy, have enhanced safety by enabling precise tracheal segmentation from endoscopic images. Our study introduces an innovative image enhancement technique for video endoscopy that significantly improves tracheal visibility and segmentation accuracy. This novel approach not only facilitates safer and more accurate intubation but also minimizes patient discomfort and procedural risks. Tested against the UoS Dataset and real patient data from thyroidectomy procedures, our method demonstrated superior performance, achieving a segmentation accuracy of $97 \%$, a precision of $94 \%$, and a recall of $99 \%$. Our tailored method is computationally efficient, making it suitable for implementation on edge devices like Arduino, thereby enhancing intubation safety and efficiency in various medical settings.

Remote photoplethysmography (rPPG) enables non-invasive extraction of blood volume pulse signals through imaging, transforming spatial-temporal data into time series signals. Advances in end-to-end rPPG approaches have focused on this transformation where attention mechanisms are crucial for feature extraction. However, existing methods compute attention disjointly across spatial, temporal, and channel dimensions. Here, we propose the Factorized Self-Attention Module (FSAM), which jointly computes multidimensional attention from voxel embeddings using nonnegative matrix factorization. To demonstrate FSAM's effectiveness, we developed FactorizePhys, an end-to-end 3D-CNN architecture for estimating blood volume pulse signals from raw video frames. Our approach adeptly factorizes voxel embeddings to achieve comprehensive spatial, temporal, and channel attention, enhancing performance of generic signal extraction tasks. Furthermore, we deploy FSAM within an existing 2D-CNN-based rPPG architecture to illustrate its versatility. FSAM and FactorizePhys are thoroughly evaluated against state-of-the-art rPPG methods, each representing different types of architecture and attention mechanism. We perform ablation studies to investigate the architectural decisions and hyperparameters of FSAM. Experiments on four publicly available datasets and intuitive visualization of learned spatial-temporal features substantiate the effectiveness of FSAM and enhanced cross-dataset generalization in estimating rPPG signals, suggesting its broader potential as a multidimensional attention mechanism. The code is accessible at https://github.com/PhysiologicAILab/FactorizePhys.

Solar panel segmentation (SPS) is identifying and locating solar panels from remote sensing images, such as aerial or satellite imagery. SPS is critical for energy monitoring, urban planning, and environmental studies, as it can provide information on the distribution and deployment of solar energy systems and their impact on the climate and the economy. However, existing methods face several challenges, such as low-quality remote sensing images, varying resolutions, and high computational costs. These factors make it challenging to distinguish solar panels from other objects or backgrounds and accurately and efficiently segment them. This paper proposes a novel HSS-Net (Hyperspectral Solar Segmentation Network) method for SPS, combining Chebyshev transformation (CHT) and hyperspectral synthetic decomposition (HSD). Our method can enhance the image quality, select the optimal bands, and segment the solar panels. We validated the presented method on three publicly available SPS benchmark datasets, such as BDAPPV, PV, and DeepSolar. We compared the performance of HSS-Net with the state-of-the-art (SOTA) methods, including CNN-based and transformer-based networks and existing hyperspectral segmentation techniques. We used the intersection over union (IoU), the F1-score, and the Kappa coefficient (KI) as the evaluation metrics. We demonstrated that HSS-Net significantly surpasses SOTA methods in terms of accuracy, efficiency, and scalability, can advance remote sensing applications, and may provide more precise results in various relevant fields.

Images captured in adverse weather conditions, such as haze, fog, smog, or mist, have reduced visibility, contrast, and color fidelity. These impairments challenge various computer vision applications, such as intelligent transportation, video surveillance, weather forecasting, and remote sensing. While many daytime dehazing techniques exist, they are less effective for nighttime images, which have additional issues, such as nonuniform illumination, texture blurring, glow effects, color distortion, noise, and low light. This paper proposes a novel method for improving the quality of nighttime images affected by haze and low-light conditions. Our method, Nighttime Dehazing, Low-Light Enhancement, and Light Suppression (NDELS), integrates three key processes: enhancing visibility, brightening low-light areas, and suppressing glare from bright light sources. We also introduce a novel method for generating training data to help our model learn light suppression better. We evaluate our method against eight state-of-the-art algorithms on four diverse datasets. The simulation results show that the presented method outperforms the state-of-the-art methods quantitatively and qualitatively. For example, our method (i) improves the overall image quality, color fidelity, and edges and (ii) achieves 8.8% higher PSNR, and 4.5% higher SSIM scores, and a better subjective rating. Moreover, our method enhances real-world object detection tasks, surpassing other methods in performance.

Real-world images captured in remote sensing, image or video retrieval, and outdoor surveillance are often degraded due to poor weather conditions, such as rain and mist. These conditions introduce artifacts that make visual analysis challenging and limit the performance of high-level computer vision methods. In time-critical applications, it is vital to develop algorithms that automatically remove rain without compromising the quality of the image contents. This article proposes a novel approach called QSAM-Net, a quaternion multi-stage multiscale neural network with a self-attention module. The algorithm requires significantly fewer parameters by a factor of 3.98 than the real-valued counterpart and state-of-the-art methods while improving the visual quality of the images. The extensive evaluation and benchmarking on synthetic and real-world rainy images demonstrate the effectiveness of QSAM-Net. This feature makes the network suitable for edge devices and applications requiring near real-time performance. Furthermore, the experiments show that the improved visual quality of images also leads to better object detection accuracy and training speed.

Single-image haze removal is challenging due to its ill-posed nature. The breadth of real-world scenarios makes it difficult to find an optimal dehazing approach that works well for various applications. This article addresses this challenge by utilizing a novel robust quaternion neural network architecture for single-image dehazing applications. The architecture's performance to dehaze images and its impact on real applications, such as object detection, is presented. The proposed single-image dehazing network is based on an encoder-decoder architecture capable of taking advantage of quaternion image representation without interrupting the quaternion dataflow end-to-end. We achieve this by introducing a novel quaternion pixel-wise loss function and quaternion instance normalization layer. The performance of the proposed QCNN-H quaternion framework is evaluated on two synthetic datasets, two real-world datasets, and one real-world task-oriented benchmark. Extensive experiments confirm that the QCNN-H outperforms state-of-the-art haze removal procedures in visual quality and quantitative metrics. Furthermore, the evaluation shows increased accuracy and recall of state-of-the-art object detection in hazy scenes using the presented QCNN-H method. This is the first time the quaternion convolutional network has been applied to the haze removal task.

Image restoration techniques process degraded images to highlight obscure details or enhance the scene with good contrast and vivid color for the best possible visibility. Poor illumination condition causes issues, such as high-level noise, unlikely color or texture distortions, nonuniform exposure, halo artifacts, and lack of sharpness in the images. This article presents a novel end-to-end trainable deep convolutional neural network called the deep perceptual image enhancement network (DPIENet) to address these challenges. The novel contributions of the proposed work are: 1) a framework to synthesize multiple exposures from a single image and utilizing the exposure variation to restore the image and 2) a loss function based on the approximation of the logarithmic response of the human eye. Extensive computer simulations on the benchmark MIT-Adobe FiveK and user studies performed using Google high dynamic range, DIV2K, and low light image datasets show that DPIENet has clear advantages over state-of-the-art techniques. It has the potential to be useful for many everyday applications such as modernizing traditional camera technologies that currently capture images/videos with under/overexposed regions due to their sensors limitations, to be used in consumer photography to help the users capture appealing images, or for a variety of intelligent systems, including automated driving and video surveillance applications.

In this letter, a new texture filter with scale-aware gradients and structural preservation is proposed. The proposed filter uses a hybrid$L_{0}$-$H^{-1} $variational model via measuring sparsity with scale-aware gradients by the$L_{0}$norm and structural fidelity by the$H^{-1}$norm with the embedded Laplacian operator. Extensive qualitative and quantitative experimental results demonstrate that the proposed method 1) smooths small-scale low/high contrast textures and intensive noise while preserving sharp and prominent structures simultaneously; 2) significantly outperforms state-of-the-art texture filtering methods; and 3) has fast convergence.

The application of Artificial Intelligence in dental healthcare has a very promising role due to the abundance of imagery and non-imagery-based clinical data. Expert analysis of dental radiographs can provide crucial information for clinical diagnosis and treatment. In recent years, Convolutional Neural Networks have achieved the highest accuracy in various benchmarks, including analyzing dental X-ray images to improve clinical care quality. The Tufts Dental Database, a new X-ray panoramic radiography image dataset, has been presented in this paper. This dataset consists of 1000 panoramic dental radiography images with expert labeling of abnormalities and teeth. The classification of radiography images was performed based on five different levels: anatomical location, peripheral characteristics, radiodensity, effects on the surrounding structure, and the abnormality category. This first-of-its-kind multimodal dataset also includes the radiologist's expertise captured in the form of eye-tracking and think-aloud protocol. The contributions of this work are 1) publicly available dataset that can help researchers to incorporate human expertise into AI and achieve more robust and accurate abnormality detection; 2) a benchmark performance analysis for various state-of-the-art systems for dental radiograph image enhancement and image segmentation using deep learning; 3) an in-depth review of various panoramic dental image datasets, along with segmentation and detection systems. The release of this dataset aims to propel the development of AI-powered automated abnormality detection and classification in dental panoramic radiographs, enhance tooth segmentation algorithms, and the ability to distill the radiologist's expertise into AI.

The coronavirus (COVID-19) pandemic has been adversely affecting people's health globally. To diminish the effect of this widespread pandemic, it is essential to detect COVID-19 cases as quickly as possible. Chest radiographs are less expensive and are a widely available imaging modality for detecting chest pathology compared with CT images. They play a vital role in early prediction and developing treatment plans for suspected or confirmed COVID-19 chest infection patients. In this paper, a novel shape-dependent Fibonacci-p patterns-based feature descriptor using a machine learning approach is proposed. Computer simulations show that the presented system (1) increases the effectiveness of differentiating COVID-19, viral pneumonia, and normal conditions, (2) is effective on small datasets, and (3) has faster inference time compared to deep learning methods with comparable performance. Computer simulations are performed on two publicly available datasets; (a) the Kaggle dataset, and (b) the COVIDGR dataset. To assess the performance of the presented system, various evaluation parameters, such as accuracy, recall, specificity, precision, and f1-score are used. Nearly 100% differentiation between normal and COVID-19 radiographs is observed for the three-class classification scheme using the lung area-specific Kaggle radiographs. While Recall of 72.65 ± 6.83 and specificity of 77.72 ± 8.06 is observed for the COVIDGR dataset.

Emulating human behaviours in automated image quality assessment (IQA) enables a comparator framework to remove the differences in human bias naturally. Based on the observation of the practical applications of IQA, this study focuses on similar‐content image quality comparison based on a new image quality comparator (IQC). Outstanding proven IQAs can be utilised in this comparator to achieve a new non‐linear combination strategy to boost the IQAs' performance in image quality comparison. For both input images to be compared, proven IQAs are utilised to obtain nine features from each image, yielding 18 total features. Then, a four‐layer comparison network conducts a classification task to indicate which input image has better quality. In the training phase, the commonly used human scores as training labels are replaced with pairwise comparison results that are automatically generated from assigned distortion level differences. By not utilising human score in training phase, this IQC shows two advantages: (i) it removes huge labor and time cost to collect the human scores and (ii) it solves the problem of over‐fitting benefiting from simplicity of creating a large image training dataset. Furthermore, the experimental tests and cross‐dataset validation comparison tests demonstrate its impressive performance.

Cross-modality face recognition is an emerging topic due to the wide-spread usage of different sensors in day-to-day life applications. The development of face recognition systems relies greatly on existing databases for evaluation and obtaining training examples for data-hungry machine learning algorithms. However, currently, there is no publicly available face database that includes more than two modalities for the same subject. In this work, we introduce the Tufts Face Database that includes images acquired in various modalities: photograph images, thermal images, near infrared images, a recorded video, a computerized facial sketch, and 3D images of each volunteer's face. An Institutional Research Board protocol was obtained and images were collected from students, staff, faculty, and their family members at Tufts University. The database includes over 10,000 images from 113 individuals from more than 15 different countries, various gender identities, ages, and ethnic backgrounds. The contributions of this work are: 1) Detailed description of the content and acquisition procedure for images in the Tufts Face Database; 2) The Tufts Face Database is publicly available to researchers worldwide, which will allow assessment and creation of more robust, consistent, and adaptable recognition algorithms; 3) A comprehensive, up-to-date review on face recognition systems and face datasets.

This paper introduces a new concept, selective color transfer (SCT), to allow for color experimentation and visualization on a selected object within an image, without affecting any other image content or color. To implement this new concept, this paper proposes a new fast SCT-I algorithm for image input data and a new SCT-V algorithm for video input data. For the SCT-I algorithm, its fundamental novelties include: 1) utilizing a new hue-division-based color region segmentation (HCR) based on defining a new nonlinear and circular property of the hue spectrum; 2) developing two new color artifact suppression strategies, including color region integration and circular statistical calculation; and 3) applying a new truncated color transfer equation to solve the problem of mismatches in the data range. The SCT-V algorithm utilizes: 1) object tracking to locate the target of interest (TOI) within each video frame; 2) the SCT-I algorithm to update the original color within TOIs; and 3) an expected color interpolation process to support different special color animation effects. The experimental results demonstrate: 1) there are no residual color artifacts introduced; 2) the approaches have tremendous flexibility for modifying an object's color; and 3) these algorithms have a low computational cost. Furthermore, these algorithms require minimal manual intervention for the easy use of ordinary users. The performance analysis demonstrates the potential of these two methods for various applications, including creating special effects in videos, making histology images much clearer for medical inspection, and enabling low-cost experimentation of manufacturing the design of a product.

The advancement of wearable eye-tracking technology enables cognitive researchers to capture vast amounts of eye gaze information while participants are completing specific tasks without restrictions on their movement. However, while eye trackers can overlay a gaze indicator on the scene video, identifying the specific objects being looked at and analyzing the resulting dataset are accomplished mostly by manual annotation. This method is a cost-prohibitive and time-consuming approach that is prone to human error. Such analytic difficulty limits researchers' ability to data mine the information efficiently, ultimately restricting the number of scenarios that can feasibly be conducted within budget. Here, the first fully automated solution for eye-tracking data analysis is presented, which eliminates the need for manual annotation. The proposed software architecture, gaze to object classification (GoC), processes the gaze-overlaid video from commercially available wearable eye trackers, recognizes and classifies the specific object a user is focusing on and calculates the gaze duration time. GoC utilizes an image cross-correlation method to locate the gaze indicator and an image similarity measurement to support faster processing. The presented system has been successfully adopted by cognitive psychologists. GoC's exceptional performance in analyzing a case study spanning over 50 h of mobile eye-tracking is presented. The accuracy and a cost-analysis comparison between GoC and state-of-the-art manual annotation software are provided. GoC has game-changing potential for increasing the ecological validity of using eye-tracking technology in cognitive research.

Fine Art Photography is one of the most popular art forms, which creates lasting impressions that elicit various human emotional reactions. Photo aesthetic enhancement aims at improving the aesthetic level of the photo to please humans by updating color appearance or modifying the geometry structure of objects within that photo. Even though several aesthetic enhancement methods have been proposed, to our knowledge, there is no research to explore, highlight, and accentuate photos’ intrinsic aesthetic value to elicit a stronger response from the human observer about the photos’ theme. To meet this challenge, a new multimedia technology called automatic color theme--based aesthetic enhancement (CT-AEA) is proposed by leveraging big online data to perform timely collection and learning of humans’ current aesthetic perception-behavior over photos and color themes in art, fashion, and design. Unlike existing aesthetic enhancement that examines the composition, such as the geometric structure of the image contents and color/luminance-related (color tone and luminance distribution) characteristics, this CT-AEA takes into consideration the importance of a suitable color theme, namely a set of dominant colors for the design when assessing the aesthetic appearance of a photo. This algorithm is composed of (1) utilizing the knowledge gained from the human evaluator's perception of beauty from existing online datasets, rather than simply applying prior existing knowledge of color harmony theory; (2) developing a new color theme difference equation that exhibits order-invariance and percentage-sensitive properties; (3) designing an optimal color theme recommendation to maximize the aesthetic performance, while minimizing the color modification cost to solve the problems of color inconsistencies and distortion. Experimental results, quantitative measure, and comparison tests demonstrate the algorithm's effectiveness, advantages, and potential for use in many color-related art and design applications.

Medical imaging systems often require image enhancement to visualize images of the human body and its organs. This would help medical professionals in irregularity or abnormality detection and diagnosis. This paper demonstrates a method to enhance medical related images. The proposed algorithm uses techniques, such as, guided filtering, edge enhancement, contrast stretching, and image fusion to enhance low resolution images. Visually, the proposed method produces better or comparable enhanced images than several state-of-the-art methods. In addition, we also test the performance of the proposed method with the method mentioned in [1].

Edge detection is an important task in image processing, and the quality of further processing is often reflected by the quality of edge detector outputs. Therefore, it is necessary to develop effective edge map quality measures to assist in evaluating the performance of edge detectors. Objective evaluation measures are crucial in automatically determining the optimal edge map for a given image or an application, as well as its parameter values. In this paper, a new reference-based edge measure (RBEM) is introduced to evaluate the performance of edge detector outputs relative to a ground truth. The new measure fuses four component metrics, based on edge pixel presence, edge corner localization, thick edge occurrence, and edge connectivity. Each of these metrics can be used separately or as a standalone measure to evaluate the quality of an edge map in terms of specific characteristics. The effectiveness of the proposed measure is demonstrated for selecting the best edge detector among several edge detectors, as well as for selecting the optimal parameter values, for both synthetic images and natural images. Experimental results show that the presented RBEM outperforms the existing methods according to subjective evaluation mean opinion scores, as it considers more important visual features in its evaluation.

Thermal image quality assessment is essential in evaluating the performance of thermal imaging systems. The existing no-reference methods can be roughly categorized using quantification measures as follows: a) Human Visual System measures, b) information measures, and c) image distribution measures. All the above classes of measures are not appropriate for thermal imaging because the structure of thermal images is quite different from visible light images. In thermal images, the temperature of the background is high, temperature difference between objects and the background is small, and it is difficult to determine the link between objective and subjective image quality assessment. There is a need in new thermal image quality measures which can connect objective representation performance and thermal image characteristics. This paper presents new no-reference thermal-imaging measures and elaborates on their applications. They integrate advantages of above-mentioned conventional of measures. Simulation results demonstrate effectiveness of the presented measures in evaluating thermal image qualities in comparison with other well-known assessment tools. Finally, conclusions on more general applicability of these measures are presented.

This paper introduces a new system for the automated classification of prostatic carcinomas from biopsy images. The important components of the proposed system are (1) the new features for tissue description based on hyper-complex wavelet analysis, quaternion color ratios, and modified local binary patterns; and (2) a new framework for multi-stage learning that integrates both multi-class and binary classifiers. The system performance is estimated by employing Hold-out cross-validation in a dataset of 71 prostate cancer biopsy images with different Gleason grades. Simulation results show that the presented technique is able to correctly classify images in 98.89% of the test cases. Furthermore, the system is robust in terms of sensitivity (0.9833) and specificity (0.9917). We have demonstrated the efficacy of our system in distinguishing between Gleason grades 3, 4 and 5.

Thermography is an imaging technique which is based on the idea that the temperature rises in regions with increased blood flow and metabolism, which could be a sign of a tumor. Recently, it has found promising applications in cancer diagnosis, particularly, in breast cancer exposure. Even though many thermo-medical applications need a good image assessment tool, there were no reports in literature on using a thermal image as a thermal conditioning of breast cancer progress/treatment. In this paper, a novel thermal images assessment tool for detecting the conditions of breast cancer exposure based on thermography is proposed. The presented innovative measure is based on integration of human visual system, intensity and density attributes of observed images. The proposed scheme as thermal conditions of breast cancer has the advantages of: (i) determining cancer risks for prevention by introducing a measuring system for estrogen imbalance, (ii) detecting the progress and treatment by monitoring the conditions as a new measurements and (iii) breast skin temperature measurement. The experiments show the effectiveness of the proposed measuring system on thermal conditions of breast cancer.

This paper introduces a novel cross-entropy Histogram Equalization method. The new algorithm is based on separating the density spectrum of an image and then minimizing the so-called Cross-Entropy between the brightness and darkness components. Cross-entropy is used to measure the information-theoretic distance between the image's brightness and darkness. Experimental results show that the cross-entropy histogram equalization method has better performance than Bi-histogram equalization and its modified weighted form.

Diagnosis of prostate cancer currently involves visual examination of samples for the assignment of Gleason grades using a microscope, a time-consuming and subjective process. Computer-aided diagnosis (CAD) of histopathology images has become an important research area in diagnostic pathology. This paper presents a scheme to improve the accuracy of existing CAD systems for Gleason grading on digital biopsy slides by combining color and multi-scale information using quaternion algebra. The distinguishing features of presented algorithm are: 1) use of the quaternion wavelet transform and modified local binary patterns for the analysis of image texture in regions of interest, 2) A two-stage classification method: (a) a quaternion neural network with a new high-speed learning algorithm used for multiclass classification, and (b) several binary Support Vector Machine (SVM) classifiers used for classification refinement. In order to evaluate performance, hold-one-out cross validation is applied to a data set of 71 images of prostatic carcinomas belonging to Gleason grades 3, 4 and 5. The developed system assigns the correct Gleason grade in 98.87% of test cases and outperforms other published automatic Gleason grading systems. Moreover, averaged over all the classes, testing of the proposed method shows a specificity rate of 0.990 and a sensitivity rate of 0.967. Experimental results demonstrate the proposed scheme can help pathologists and radiologists diagnose prostate cancer more efficiently and with better reproducability.

This paper introduces a new parametric n-ary Gray code, the (n, k, p)-Gray code, which includes several commonly used codes such as the binary-reflected, ternary, and (n, k)-Gray codes. The new (n, k, p)-Gray code has potential applications in digital communications and signal/image processing systems. This paper focuses on three illustrative applications of the (n, k, p)-Gray code, namely, image bit-plane decomposition, image denoising, and encryption. The computer simulations demonstrate that the (n, k, p)-Gray code shows better performance than other traditional Gray codes for these applications in image systems.

Image enhancement is a crucial pre-processing step for various image processing applications and vision systems. Many enhancement algorithms have been proposed based on different sets of criteria. However, a direct multi-scale image enhancement algorithm capable of independently and/or simultaneously providing adequate contrast enhancement, tonal rendition, dynamic range compression, and accurate edge preservation in a controlled manner has yet to be produced. In this paper, a multi-scale image enhancement algorithm based on a new parametric contrast measure is presented. The parametric contrast measure incorporates not only the luminance masking characteristic, but also the contrast masking characteristic of the human visual system. The formulation of the contrast measure can be adapted for any multi-resolution decomposition scheme in order to yield new human visual system-inspired multi-scale transforms. In this article, it is exemplified using the Laplacian pyramid, discrete wavelet transform, stationary wavelet transform, and dual-tree complex wavelet transform. Consequently, the proposed enhancement procedure is developed. The advantages of the proposed method include: 1) the integration of both the luminance and contrast masking phenomena; 2) the extension of non-linear mapping schemes to human visual system inspired multi-scale contrast coefficients; 3) the extension of human visual system-based image enhancement approaches to the stationary and dual-tree complex wavelet transforms, and a direct means of; 4) adjusting overall brightness; and 5) achieving dynamic range compression for image enhancement within a direct multi-scale enhancement framework. Experimental results demonstrate the ability of the proposed algorithm to achieve simultaneous local and global enhancements.

Vascular segmentation through the use of image processing tools provides significant information that allows for the accurate diagnosis, categorization, registration, and visualization of vascular disease. Currently, in the assessment of Abdominal Aortic Aneurysms (AAA), radiologists manually segment different regions on interest on each medical image to create a full volume of the abdominal aorta. Such manual segmentation is a time consuming task, prone to errors and a subjective approach especially when non-contrast enhanced images are present. In this paper, we introduce an automatic system to segment the aortic lumen in non-contrast enhanced CT scans and PC-MR images using digital image processing algorithms where image enhancement, denoising, edge detection, and regional growing algorithms are utilized. The output of this work forms the basis for a future reliable inner and outer wall segmentation of the AAA.

Prostate cancer automatic grading has attracted a lot of attention during the last years [1]. Many research efforts have been fixated on the development of computerized recognition and classification systems to automatically grade Gleason patterns. Automatic computerized Gleason grading methods can be classified into two basic classes: image textural-based class and tissue structural-based (nuclear architecture, gland morphology) class. To the best of our knowledge, tissue structural classification based on three-class classification results including Gleason grade 3, 4 and 5 carcinoma were not reported. The goal of this article is to: (1) develop computerized assessment support systems to automatically grade Gleason patterns 3, 4 and 5 by integrating gland morphology and architectural features; (2) improve classification accuracy especially between intermediate Gleason grades 3 and 4. Computer simulations show an average correct classification accuracy of 97.63%, 96.57% and 87.30% when distinguishing Gleason 3 vs. Gleason 4, Gleason 3 vs. Gleason 5, and Gleason 4 vs. Gleason 5 respectively. These results lead the way towards providing an effective and promising software tool in automatic prostate cancer histological Gleason grading.

Leukemia is a type of cancer that affects the blood and the bone marrow. Manual data analysis is time consuming and not accurate. Attempts to build partial/full automated systems based on segmentation and classification of cells are present in literature, but they are still in prototype stage. Most of the existing automatic systems extract features of the sub-images instead of the complete blood smear. [29]. The main objective of this paper is to a) demonstrate that the classification of peripheral blood smear images containing multiple nuclei can be fully automated, b) to validate the segmented images using hold-out cross validation method. The method has been evaluated using a set of 50 images (with 25 abnormal samples and 25 normal samples) obtained from American Society of Hematology [22]. The computer simulations show that the proposed system robustly segments and classifies Acute Myelogenous Leukemia based on complete microscopic blood images. 93.5% of the cases were correctly classified by the program, suggesting that the method yields good results in terms of classification of leukemia. The developed system can be used as ancillary/backup service to the physician.

The aim of this study is to develop a method of lesion extraction from a large image of a skin surface and evaluate a new set of color features and their ability to classify the extracted skin lesions. It is beneficial for a dermatologist to be able to take a snapshot of a large skin surface and have an automated system locate and diagnose atypical lesions. The proposed system accomplishes this task and is designed to be used by dermatologists as a completely integrated analytical tool to improve the rate of correct diagnosis well above 90%. Simulations are implemented to show extraction of skin lesions and how their features are measured as well as classification results. The outcomes showed that the computer aided diagnosis model discussed in this paper has an improved classification performance and is an objective diagnostic tool that can be used in medical practice.

In this Paper, we introduce a new method for automatic recognition and classification of prostate cancer biopsy images based on Gleason grading system. The introduced algorithm combines features from wavelet transform and fractal analysis domains. Biopsy images are pre-processed prior to features extraction using effective image processing algorithms to analyze textural complexity in terms of RGB color channels, edge and segmentation information. Experimental results achieved an average classification accuracy of 95 % in a set of 45 images with diversities in resolution, magnification levels, and stain colors.

In this paper, a new extension of Bidimensional Empirical Mode Decomposition (BEMD) based on the median filtering is presented. The new scheme is compared with the traditional Empirical Mode Decomposition (EMD) and Fast and Adaptive Bidimensional EMD (FABEMD) techniques. The new scheme manifests to be superior to both of them in image enhancement and particularly in edge enhancement. The comparison is performed, objectively, using the measure of enhancement (EME) and also visually. Furthermore, we show that by applying different thresholds in stopping condition for each Intrinsic Mode Function (IMF), we can derive more accurate IMFs.

In this paper, we introduce two novel edge detection algorithms based on a negative alpha weighted quadratic filter. The goal of this work is to utilize the characteristics of the nonlinear filter to preserve and enhance edges for the purpose of edge detection. Unlike traditional edge detection algorithms, which detect edges by using derivatives, the proposed algorithms operate on local regions and modify the color tones of uniform regions while preserving the original edges. We also incorporate the luminance masking feature of the Human Visual System by masking the gradient image before edge labeling. Experimental simulations show that the proposed algorithms can extract fine edge information from images contaminated by noise and affected by non-uniform illumination; the obtained edge maps are more consistent to the edges perceived by the human eye. Comparison with existing algorithms will be also presented.

In this paper, we propose a new algorithm based on Fourier spectral characteristics. This technique improves the coding prediction accuracy, boosting the protein coding region and suppressing the non-coding region within the DNA sequences. We also compare this algorithm using computer simulation with commonly used techniques showing that our technique for exon region prediction provides superior properties for the separation of exon and intron regions.

Because of its ability to compress and encrypt plaintext simultaneously, embedment of stream cipher rules into Elias-type entropy encoders provides a fast and secure means of data compression with the ability to hide cipherstream information in the case of a known plaintext attack. Compression and security improve by continually updating the statistical representation of the plaintext. Simulations on images from a variety of classes compare the compression ratios and computational costs of the novel system to those of traditional compression-followed-by-encryption methods.

Image fusion algorithms combine images obtained using different sensors into a single image to provide contextual enhancement of the scene being observed. The fusion of images obtained using infrared (IR) and visible light (VL) cameras are particularly appealing for security applications such as surveillance and concealed weapon detection. In this paper, a new image fusion algorithm is proposed, which considers both the luminance masking feature of the human visual system (HVS) and the nature of the pertinent information in IR images in the context of surveillance applications. Experimental results illustrate the improved performance of the proposed algorithm by both qualitative and quantitative means.

Vanilla is the second most expensive spice worldwide. The high cost of vanilla has led to the problem of dangerous adulterated substitutes. Its high cost is attributed largely to the labor intensive hand pollination required where the melipona bee is not present. This article proposes a method of segmenting vanilla images intended for robotic control of a future automated pollination system. We present the specialization of a hypercomplex numbers based segmentation technique for vanilla flower recognition. The specialization overcomes much of the difficulty of differentiating green flowers from their similarly colored surroundings. Comparison is given to previous hypercomplex numbers based segmentation without the specialization.

In this paper, a new information entropy based randomness test for image encryption about is proposed. Unlike the conventional information entropy test working on the global image, the new proposed measurement focuses on local image blocks and calculates the sample mean of information entropy over a number of random selected image blocks within a test encrypted image. Reference values are mathematical derived from the ideally encrypted image model. As a result, the randomness of an encrypted image can be easily told by comparing the test values with theoretical ones. Ultimately, a hypothesis test to accept or reject an encrypted image is also derived to accept or reject the null hypothesis that ciphertext image is ideally encrypted/random-like with a significance level α. In such a way, the proposed block entropy test provides both quantitative and qualitative results for image encryption. Experimental results on existing image cipher show the effectiveness of the proposed test. The same idea can be also to other digital data, like videos or audios.

S-Boxes play a vital role in cipher designs and have been researched for years. In this article a new way of dynamically designing S-boxes using Latin Square doubly stochastic matrix is proposed. And it is demonstrated that the enciphering/deciphering process is a mimic of a Markov chain Monte Carlo simulation. Unlike conventional dynamic S-boxes, the proposed S-boxes are not directly defined by keys, but contained in the key dependent doubly stochastic matrix. The created matrix has desired properties including: 1) it implicitly contains S-boxes and thus complicates the internal structure of S-boxes; 2) it naturally defines S-boxes with reversibility and thus any S-boxes used for encryption can be directly used for decryption; 3) it satisfies the Strict Avalanche Criterion (SAC) for S-Boxes and thus it has good resistance to differential or linear cryptanalysis; 4) it guarantees the independence of the ciphertext distribution from plaintext one; and 5) it ensures that the expected ciphertext distribution is uniform and thus attains excellent confusion properties when use these S-Boxes iteratively. Theoretical and experimental results show that the proposed S-box has a high security level and is suitable to design cryptosystem for data encryption. We also extend our S-boxes to a simple image cipher. Experimental results show that the proposed dynamical flexible structure S-boxes has cryptographic properties comparable or better than some existing image encryption methods.

This paper presents a novel modified multi scale contrast enhancement (MMCE) technique for color image enhancement based on manipulating the DCT coefficients. Modified multi contrast enhancement (MCE) is an improved version of multi contrast enhancement by redefining the frequency spectral bands and introducing more band enhancement techniques to achieve a better performance. This paper also uses an image contrast measure SDME to choose the optimal parameters and to demonstrate the effectiveness of the methods. Computer simulations and analysis are shown that the presented method outperforms the commonly used methods such as Retinex and the original MCE for most images.

This paper introduces a new unsharp masking (UM) scheme, called nonlinear UM (NLUM), for mammogram enhancement. The NLUM offers users the flexibility 1) to embed different types of filters into the nonlinear filtering operator; 2) to choose different linear or nonlinear operations for the fusion processes that combines the enhanced filtered portion of the mammogram with the original mammogram; and 3) to allow the NLUM parameter selection to be performed manually or by using a quantitative enhancement measure to obtain the optimal enhancement parameters. We also introduce a new enhancement measure approach, called the second-derivative-like measure of enhancement, which is shown to have better performance than other measures in evaluating the visual quality of image enhancement. The comparison and evaluation of enhancement performance demonstrate that the NLUM can improve the disease diagnosis by enhancing the fine details in mammograms with no a priori knowledge of the image contents. The human-visual-system-based image decomposition is used for analysis and visualization of mammogram enhancement.

The five papers in this special issue focus on pattern recognition technologies for anti-terrorism applications.

Image processing technologies such as image enhancement generally utilize linear arithmetic operations to manipulate images. Recently, Jourlin and Pinoli successfully used the logarithmic image processing (LIP) model for several applications of image processing such as image enhancement and segmentation. In this paper, we introduce a parameterized LIP (PLIP) model that spans both the linear arithmetic and LIP operations and all scenarios in between within a single unified model. We also introduce both frequency- and spatial-domain PLIP-based image enhancement methods, including the PLIP Lee's algorithm, PLIP bihistogram equalization, and the PLIP alpha rooting. Computer simulations and comparisons demonstrate that the new PLIP model allows the user to obtain improved enhancement performance by changing only the PLIP parameters, to yield better image fusion results by utilizing the PLIP addition or image multiplication, to represent a larger span of cases than the LIP and linear arithmetic cases by changing parameters, and to utilize and illustrate the logarithmic exponential operation for image fusion and enhancement.

This paper presents a new system that reconstructs and visualizes 3D Purkinje cells (neurons) from two-photon microscopy images. The main components of the system are nonlinear diffusion filtering for denoising of each two-photon microscopy slice, increasing the image resolution of each Purkinje cell slice, global image enhancement of each slice as well as local pixel based image enhancement of each slice. Finally, 3D reconstruction and visualization of the Purkinje cell is accomplished using ImageJ. Computer simulations will illustrate the elucidated improvements over the original Purkinje cell images. Specifically, the presented system brought out hidden dendrite branches and allowed for a clearer picture of the entire Purkinje cell.

The need of encrypted data has increased in our day to day life. In this paper, we discuss an encryption technique based on Logical Transforms. The secret keys used in this technique to encrypt the images were based on the logical transforms that satisfies proposed boolean matrix constraints. In addition novel lossless encryption technique is introduced for the images of arbitrary size and format. This method can also be implemented on hardware.

In this paper, we present an algorithm for visualizing edges in RGB colored images as well as edge detection using logarithmic ratio approach. The developed visualization algorithm has a superior performance in highlighting more unforeseen color edges than the standard RGB-grayscale conversion method can present. Also, by integrating the proposed algorithm with a logarithmic-ratio based edge detector operator, the developed algorithm outperforms the standard edge detection operators in gradient colored images where color boundaries transitions are hard to detect.

Selective regional encryption was performed on nonrectangular, statistically relevant regions of image media by permutation of coefficients in the domain of a fast, shape adaptive, parametric transform in order to partially encrypt the original image. Regions were successfully segmented using a high order information analysis. A simple encryption scheme which exploits the energy compaction properties of a shape adaptive cosine transform was then applied in the transform domain. Computer simulation shows that the method is fast and statistically secure.

Image fusion is the process of combining multiple images into a single image which retains the most pertinent information from each original image source. More recently, multi-scale image fusion approaches have emerged as a means of providing a more meaningful fusion which better reflects the human visual system. In this paper, multi-scale decomposition techniques and image fusion algorithms are adapted using the Parameterized Logarithmic Image Processing (PLIP) model, a nonlinear image processing framework which more accurately processes images. Experimental results via computer simulations illustrate the improved performance of the proposed algorithms by both qualitative and quantitative means.

This paper presents a multi tier web architecture that integrates web technology, Database system, and Batch processing tools for the development of a real time threat detection system. Four data repository models are introduced for effective data storage and retrieval. The baseline feature vectors are introduced and stored in the database table using a batch job. The batch job performs load balancing by calculating the new feature vector using the offline server and updates the online database server. The illustrative application uses the Hierarchical Multi level HVS segmentation, ratio based edge detection, and support vector machine for threat recognition and detection. The 64 bit edge based feature vector is generated for the baseline images and the input test object images using the cell edge distribution approach. The experimental results demonstrate that the presented framework is efficient in facilitating accurate threat detection and support the development of portable, reusable and scalable object recognition applications for heterogeneous distributed environment.

This paper presents a novel block cipher based on the Sudoku matrix. The offered block cipher combines many advantages of chaos-based encryption and traditional transform-based encryption techniques. Computer simulations show that a) the encrypted data have very random-like properties under many statistical metrics, b) unlike most chaos-based encryption methods generating unpredictable output, our new method is robust and effective for generating uniform-like encrypted data; c) it has high sensitivity to the KEY. The offered scheme can be applied to many different data types, such as audio, image and video.

This paper introduces a new enhancement algorithm for prostate MR images using a new nonlinear filtering operation and an alpha-trimmed Mean Separation. A new enhancement measure is also introduced to measure and assess the enhanced results. Experimental results show that the presented algorithm can significantly improve the contrast of prostate MR images. It has a potential application in prostate cancer detection.

This paper introduces a new concept of Boolean derivatives as a fusion of partial derivatives of Boolean functions (PDBFs). Three efficient algorithms for the calculation of PDBFs are presented. It is shown that Boolean function derivatives are useful for the application of identifying the location of edge pixels in binary images. The same concept is extended to the development of a new edge detection algorithm for grayscale images, which yields competitive results, compared with those of traditional methods. Furthermore, a new measure is introduced to automatically determine the parameter values used in the thresholding portion of the binarization procedure. Through computer simulations, demonstrations of Boolean derivatives and the effectiveness of the presented edge detection algorithm, compared with traditional edge detection algorithms, are shown using several synthetic and natural test images. In order to make quantitative comparisons, two quantitative measures are used: one based on the recovery of the original image from the output edge map and the Pratt's figure of merit.

In this paper we introduce an improved Canny edge detection algorithm and an edge preservation filtering procedure for asphalt concrete (AC) applications. Datasets of AC images were randomly selected to test this algorithm. Computer simulations show that the improved algorithm can make up for the disadvantages of Canny algorithm, detect edges of AC images effectively, and is a less time-consuming process. Particularly, it has been shown that the presented algorithm can not only eliminate noises effectively but also protect unclear edges.

The prompt delivery of biomedical images for emergency diagnosis purpose is an important issue in health care organizations. This paper is aimed a developing class of algorithms to view and manipulate medical images on mobile devices and mainly PDA handhelds. We illustrate our method on human brain scans to view: 2-D single medical imaging scans, multi frames/slices medical imaging scans, internal 3-D anatomical details of a simulated straight line-cut, and the reconstruction of the original scanned object e.g. the original head image.

In information security, steganalysis has been an important topic since evidences first indicated steganography has been used for covert communication. Among all digital files, numerous devices generate JPEG images due to the capability of compression and compatibility. A large number of JPEG steganography methods are also provided online for free usage. This has spawned significant research in the area of JPEG steganalysis. This paper introduces an image estimation technique utilizing the alpha-trimmed mean for distinguishing clean and steganography images. The hidden information is considered additive noise to the image. The alpha-trimmed method estimates steganographic messages within images in the spatial domain and provide flexibility for classifying various steganography methods in the JPEG compression domain. For three JPEG steganography methods along with three embedding message files applied to an image data set, the proposed method results in better separability between clean and steganographic classes. The results are based on comparisons between the presented method and two existing methods in which classification accuracies are increased by as much as 32%.

Current technology allows steganography applications to conceal any digital file inside of another digital file. Due to the large number of steganography tools available over the Internet, a particular threat exists when criminals use steganography to conceal their activities within digital images in cyber space. In this paper, a set of statistical features are generated using linear mixed effects models in conjunction with wavelet decomposition for image steganography detection. It is important to generate features capable of distinguishing between a set of clean and steganography images for steganalysts in commercial industry, Department of Defense, government as well as law enforcement. In the experimental results, seven sets of images are used to measure the performance of the proposed method, a clean set and two JPEG steganography methods with three different embedding file sizes to create steganography images. The number of correct predictions that an instance is clean or steganographic are improved by as much as 38% when using the proposed linear mixed effects models compared to the linear fixed effects models.

This paper presents a direct method of reducing convolution processing time using hardware computing and implementations of discrete linear convolution of two finite length sequences (NXN). This implementation method is realized by simplifying the convolution building blocks. The purpose of this research is to prove the feasibility of an application specific integrated circuit (ASIC) that performs a convolution on an acquired image in real time. The proposed implementation uses a modified hierarchical design approach, which efficiently and accurately speeds up computation; reduces power, hardware resources, and area significantly. The efficiency of the proposed convolution circuit is tested by embedding it in a top level FPGA. Simulation and comparison to different design approaches show that the circuit uses only 5 mw that saves almost 35% of area and is four times faster than what is implemented in. In addition, the presented circuit uses less power consumption and has a delay of 20 ns from input to output using 32 nm process library. It also provides the necessary modularity, expandability, and regularity to form different convolutions for any number of bits.

This parameterized digital electronic arithmetic (PDEA) model replaces linear operations with non-linear ones. In this paper we introduce a hardware implementation of the parametric image-processing framework that will accurately process images and speed up computation for addition, subtraction, and multiplication. Particularly, the paper presents the design of arithmetic circuits including parallel counters, adders and multipliers based in two high performance threshold logic gate implementations that we have developed. We also explore new microprocessor architectures to take advantage of arithmetic. The experiments executed have shown that the algorithm provides faster and better enhancements from those described in the literature. Its potential applications include computer graphics, digital signal processing and other multimedia applications.

We propose Reduced Voltage Swing (RVS) signaling (by elevating the logic 0 voltage) as opposed to Low Voltage Swing (LVS) signaling (which reduces the logic 1 voltage). We propose an inverter which generates RVS signals, and an extension with programmable logic for adjusted logic 0 voltage. The proposed RVS scheme achieves reduced active power consumption, minimum performance degradation and minimum area overhead (without extra power supply network and a minimum number of extra transistors). Application of multi-threshold voltage design further alleviates compromises on noise margin and leakage. Experimental results based on SPICE simulation show that RVS clocking achieves an average of 37% active power consumption reduction, 8% performance degradation.

Edge detection has been used extensively as a preprocessing step for many computer vision tasks. Due to its importance in image processing and the highly subjective nature of human evaluation and visual comparison of edge detectors, it is desirable to formulate objective edge map evaluation measures. One would like to use such a measure to make comparisons of results using the same edge detector with different parameters as well as to make comparisons of results using different edge detectors. Reconstruction-based measures have the clear advantage that they effectively incorporate original image data. In this paper, a general model for reconstruction-based measures is established in order to alleviate the shortcomings of the reconstruction-based measures, followed by the formulation of a new non-reference measure for objective edge map evaluation. Experimental results illustrate the effectiveness of the new measure both as a means of selecting optimal edge detector parameters and as a means of determining the relative performance of edge detectors for a given image.

A novel digital forensics tool is developed by combining wavelet invariant with spatial moments. A forensic printed circuit board image matching system is presented that is capable of probing a large database of digital images of circuit boards and compare them for similarity to provide investigation leads for electronic crimes digital forensic science investigations. The developed system has been implemented, and proved to be very efficient in detection similarities between a target image and a large image database even when the target image is noisy, scaled or mirrored.

This paper introduces a new concept for image encryption using a binary ¿key-image¿. The key-image is either a bit plane or an edge map generated from another image, which has the same size as the original image to be encrypted. In addition, we introduce two new lossless image encryption algorithms using this key-image technique. The performance of these algorithms is discussed against common attacks such as the brute force attack, ciphertext attacks and plaintext attacks. The analysis and experimental results show that the proposed algorithms can fully encrypt all types of images. This makes them suitable for securing multimedia applications and shows they have the potential to be used to secure communications in a variety of wired/wireless scenarios and real-time application such as mobile phone services.

Summary form only given. Significant work has been performed on encrypting images and compressing images as two separate problems, but traditional encryption techniques generally degrade the compression ratio. To circumvent these issues, two methods have been used. The first employs known encryption algorithms on compressed image data. The second develops compression algorithms which work well for encrypted data. The contribution of this paper is using alpha rooting to perform simultaneous compression and encryption. This achieves improved compression performance in terms of computational complexity and compression ratio. Results are shown for 2 of the well known benchmark images, using the well known JPEG image compression standard to demonstrate the effectiveness of alpha rooting for simultaneous encryption and compression.

This paper presents the new Fibonacci Fourier-like transforms. The proposed transforms render the relationship between Fibonacci numbers and the conventional Discrete Fourier Transform. The fast Fibonacci Fourier transforms are also introduced with the use of the Kronecker product properties. The proposed transforms are applied to the problem of noise reduction with two new algorithms, sliding double window filtering and fusion sliding window filtering. The primary concept of sliding double window filtering is to process the noisy signals with nonoverlapped windows, while the primary concept of fusion sliding window filtering is to process the noisy signals with various weighted filtering methods and overlapped signal values. The results and analysis show the noise reduction of the given noisy gray level images. The proposed methods are compared with the well-known Wiener filtering using images that contain Gaussian noise with the range of variance between 0 and 0.3. The analysis shows by visual inspection that the noisy parts are smoothened while retaining natural edges.

In recent years, various steganography and steganalysis methods have been proposed. Collage steganography, a new type of steganographic method, has been introduced to hide the secret message in a way other than the traditional methods. The limitation of the method is the capacity. This paper presents a new generalized collage steganography, an extension of collage steganography, to improve the capacity problem. The secret message is hidden by incorporating object images with transparent features into a cover image. A proper cover image is chosen based on prior capacity analysis. The selected object image and the translation, rotation and scaling factors in the affine transformation are used to hide the secret message as well as the image pixels, coefficients and/or header files. The appearance of the cover image is changed due to the addition of the object image for embedding. The information is retrieved via template matching techniques. The results demonstrate the relationship between different images and its capacity. Several steganographic image examples are illustrated. Comparisons between the collage steganography and the generalized collage steganography show a higher capacity when using the new steganographic method.

Extraction of the edges is a key step in image processing and there is still a continuing research effort to develop new and effective edge detection algorithms. Despite this fact, there is no single, reliable and efficient metric to evaluate the quality of an edge detector. We introduce an original method for image reconstruction that leads to edge evaluation based on image estimation. A new quantitative metric for assessment of the performance of the edge detector is also presented. The operation of the measure is established on a diverse image database using standard edge detection algorithms and the one based on partial derivatives of Boolean functions. The uses of the measure for an assortment of purposes are demonstrated and these are backed by visual assessment as well as some distance-based error functions applied on synthetic images.

Feature extraction is arguably the most important stage of an automatic object detection system. It is in this stage where the results of previous processing steps are interpreted to somehow characterize an object. Developing methods for feature extraction and feature vector generation using information from edge maps is a natural progression, as edge detection determines structure in images. A new edge-based feature extraction scheme is introduced based on the feature fusion of two existing methods. A generalized set of kernels for edge detection is also presented. The experimental results show that the detection of different objects of interests is improved using the new method.

In this paper we present a novel image quality measure for color images. This measure is based on the correlation of information between color planes and principal component analysis conversion of a color image into grayscale. Furthermore, a scheme for boundary detection based on this principle is developed and presented. This innovative design utilizes partial derivatives of Boolean functions for edge detection and is then analyzed using our new measure. Results testing the scheme on a database of natural and synthetic images show the performance to be quantitatively competitive with existing measures.

Objective assessment of image quality is important for a number of image processing applications. Similarity metrics have been used for methods such as automating compression, automating watermarking, and benchmarking algorithm success. The goal of objective quality assessment is to quantify the quality of images in a manner consistent with human perception. For this reason, we introduce a novel image similarity metric based on the human visual system. The measures of enhancement (EME, AME, and LogAME) have been successfully used to quantify human quality perception for image enhancement. In this paper, we present a modified version of the Logarithmic AME which can successfully be used to quantify image similarity. We compare the quantitative assessments of this algorithm with those of the well known Mean Squared Error (MSE), Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) on the basis of correlation with subjective human evaluations for a number of images.

Image scrambling is an effective method for providing image security. This paper compares and discusses the effectiveness of some image scrambling algorithms based on recursive sequences such as the fibonacci number, generalized Fibonacci number, gray code, generalized gray code, generalized P-gray code, P-Fibonacci, P-Lucas, P-recursive sequences, and parametric M-sequences for image scrambling. The comparison of these methods for image security is based on three basic types of attacks: data loss attacks, noise attacks and plaintext attacks. The experimental results demonstrate that the scrambling algorithms based on both P-Fibonacci and P-Lucas sequences show better performance when subjected to attacks and also in terms of algorithm execution analysis which shows implementation efficiency and low computational requirements. This makes them suitable for real-time applications.

Direct sequence spread spectrum (DSSS) correlators synchronize received signals with locally generated replicas. They can be implemented either in time or frequency domains. Time-domain correlators are more flexible in multimode operations, and they are typically preferred in hardware-based implementations. Frequency-domain approaches are more computationally efficient, which makes them attractive for software-based solutions. As an alternative to frequency-domain methods, this letter derives computationally-fast time-domain algorithm using the pseudorandom and binary structure of widely used DSSS signals. Our approach is multiplication-free and accurate, it is efficient for multimode operations requiring limited number of correlator outputs, and no constraints are imposed on sequence lengths.

This letter presents a new class of polynomial threshold operators for denoising signals using wavelet transforms. The operators are parameterized to include classical soft-and hard-thresholding operators and have many degrees of freedom to optimally suppress undesired noise and preserve signal details. To avoid the complicated process of signal model identification for specific type of signals, a least squares optimization method is proposed for the polynomial coefficients. Our study shows that the proposed term-by-term, fixed-threshold operator can perform as well as adaptively applied, scale-dependent soft and hard thresholding approaches.

This paper presents a new concept of removing impulse noise through primary implicant elimination (PIE) applied to a logical system representation of the data. Applicable to binary and grayscale images, errors are corrected efficiently, in terms of the number of computations and memory requirements, while the fine details of the image are mostly preserved. Three filtering algorithms are presented: a general form in addition to iterative and switching variations. Experimental results on salt-and-pepper impulse noise, as well as on random-valued impulse noise, are compared against the performance of traditional median-based filters (both regular and switching) and are shown to be most successful in the often difficult case of when the original image contains many detailed patterns.

Varying scene illumination poses many challenging problems for machine vision systems. One such issue is developing global enhancement methods that work effectively across the varying illumination. In this paper, we introduce two novel image enhancement algorithms: edge-preserving contrast enhancement, which is able to better preserve edge details while enhancing contrast in images with varying illumination, and a novel multihistogram equalization method which utilizes the human visual system (HVS) to segment the image, allowing a fast and efficient correction of nonuniform illumination. We then extend this HVS-based multihistogram equalization approach to create a general enhancement method that can utilize any combination of enhancement algorithms for an improved performance. Additionally, we propose new quantitative measures of image enhancement, called the logarithmic Michelson contrast measure (AME) and the logarithmic AME by entropy. Many image enhancement methods require selection of operating parameters, which are typically chosen using subjective methods, but these new measures allow for automated selection. We present experimental results for these methods and make a comparison against other leading algorithms.

Images that do not have uniform brightness pose a challenging problem for image enhancement systems. As histogram equalization has been successfully used to correct for uniform brightness problems, we propose a new histogram equalization method that utilizes human visual system based thresholding as well as logarithmic processing techniques. Whereas previous histogram equalization methods have been limited in their ability to enhance these images, we demonstrate the effectiveness of this new method by enhancing a range of images with shadowing effects and inconsistent illumination. The images shown include images captured professionally and with cell phone cameras. Comparison with other methods are presented.

This paper introduces coordinate logic (CL) transforms as an alternative method for calculating coordinate logic (CL) filters. Additionally, a new measure and detection technique are introduced, enhancing the capabilities of the basic CL transform for the application of detecting edges within 2D signals (images). Applicable to binary and grayscale images, computer simulations demonstrate the success of this improved procedure on two classes of signals: synthetic (edge maps are know) and natural (edge maps are unknown). Results are evaluated quantitatively (via Pratt's figure of merit) and compared visually to two common edge detection techniques.

In this article, we present a new sensitive data detection feedback system. The basic components of this system are: a) localization of hidden data techniques and b) common and the new decision making techniques. The decision making statistical tests include: chi-square, parametric chi, Kolmogorov-Smirnov and F-test. Computer simulations will show that the proposed method provides a good localization for both randomly and sequentially embedded sensitive data. Finally, the presented system may work for both: compressed and non-compressed cases. Comparison with common existing steganalysis methods will also be presented.

Acoustic signals such as speech and music are commonly used in our day to day life. In recent years, the framework for hiding data into digital audio signals has received extensive research consideration. In this paper, we present a novel mechanism for effective encoding and decoding of hidden data into audio signal's transformed coefficients by decomposing them into Fibonacci bit-lines. Fibonacci bit-lines offer more potential space for data-hiding (since the number of Fibonacci bit-lines is higher than the traditional bit-lines). The proposed technique aims at: i) improving the capacity of the system; ii) improving the stego imperceptiveness; iii) selecting the best audio signal for hiding data from a class of signals; and iv) establishing a covert communication over a public audio channel. The embedded information could be retrieved without prior knowledge of the cover signal. The simulation results were performed over 25 various acoustic signals. In addition, future enhancements of the proposed system are discussed.

Steganalysis is the art and science of detecting hidden information. Within steganalysis there are two fundamentally different methods of defeating steganography, known as the passive and active wardens. Within the context of steganography, the most commonly researched area is the passive warden. The passive warden analyzes all messages with the intent of detecting the presence of steganography. The active warden modifies messages with the intent of destroying steganography. The active warden is an equally challenging topic, given the need for the removal of steganography to remain secret. In this paper we present the problem of the active warden and explore the application of various denoising techniques in a study in defeating steganography through active methods.

In real world machine vision problems, issues such as noise and variable scene illumination make edge and object detection difficult. There exists no universal edge detection method which works under all conditions. In this paper, we propose a logarithmic edge detection method. This achieves a higher level of scene illumination and noise independence. We present experimental results for this method, and compare results of the algorithm against several leading edge detection methods, such as Sobel and Canny. For an objective basis of comparison, we use Pratt's Figure of Merit. We further demonstrate the application of the algorithm in conjunction with Edge Detection based Image Enhancement (EDIE), showing that the use of this edge detection algorithm results in better image enhancement, as quantified by the Logarithmic AME measure.

Many applications of histograms for the purposes of image processing are well known. However, applying this process to the transform domain by way of a transform coefficient histogram has not yet been fully explored. This paper proposes three methods of image enhancement: a) logarithmic transform histogram matching, b) logarithmic transform histogram shifting, and c) logarithmic transform histogram shaping using Gaussian distributions. They are based on the properties of the logarithmic transform domain histogram and histogram equalization. The presented algorithms use the fact that the relationship between stimulus and perception is logarithmic and afford a marriage between enhancement qualities and computational efficiency. A human visual system-based quantitative measurement of image contrast improvement is also defined. This helps choose the best parameters and transform for each enhancement. A number of experimental results are presented to illustrate the performance of the proposed algorithms.

In this paper, we introduced a new Hartley transform algorithm with linear multiplicative complexity. The proposed algorithm not only minimizes the number of multiplications, but also reduces the total number of operations (arithmetic complexity, or the number of multiplications and additions) compared to the existing and recently published methods.

This paper examines the process of detecting edges using partial derivatives of Boolean functions in noisy multimedia environments. Applicable to binary and multi-bit (grayscale) data, this novel approach examines the binary representation of the original data to reconstruct edge locations within the scene. Competitive with traditional detectors in noise-free situations, the strength is its ability to detect edges in corrupted signals with no need for pre-filtering. Evaluation is performed on several synthetic and natural 2D images corrupted with impulse noise

In this paper, we have presented a new fast Fourier transform representation based cryptographic (encryption) system for the multimedia data security. The key features of the proposed system are: 1. Mapping/representation of the fast Fourier transforms' structure based on discrete orthogonal transforms, such as Walsh-Hadamard, Haar, and complex Walsh-Hadamard, etc. 2. The efficient implementations of the encryption within the core of the fast Fourier transform (flexibility in the shuffling of the sensitive information). In addition to these key features, the computational complexity of the system is comparable with commonly used methods. One of the important differences between the existing transform based encryption systems, and the proposed is that the encryption has been done in the core of the transform, which ultimately provides the highest level of security to the sensitive data. The proposed system consequently has the dual key security feature, which consists of the encryption and the transform dependent keys.

Due to the rapid developments in multimedia, the demand for binary media (such as signatures, scanned documents and images) based steganographic system has enhanced. In this paper, we present a new data-hiding system that could hide considerable amount of data into a binary digital media. The system modifies the maximum flippable pixels in each block based on certain statistics constraints and characteristic measure of the block. Thus equalizing, the uneven distribution of the flippable pixels through out the embeddable image blocks. We also discuss various issues surrounding the variable block embedding rate and the solution to those issues to make it feasible. The embedded information can be reconstructed without prior knowledge of the cover. The performance of the proposed embedding system with respect to the security and robustness is also discussed. Comparisons with the commonly used embedding systems are also presented for maximum capacity and visual distortion.

This paper presents an algorithm for breaking the JPEG based steganographical algorithms such as F5, one of the most robust information hiding systems. The detection technique is based on spatial-frequency feature vector fusion and SVM classification. First, the proposed method extracts features from spatial domain and DCT domain respectively. Second, the data fusion technique is employed to combine their features. Finally, SVM is used to classify the stego images and non-stego images based on the combined features. Owing to the unique concatenation of two domain features, the proposed algorithm shows high sensitivity to the secret messages of small sizes, allowing a more effective attack.

Steganography (stego) is used primarily when the very existence of a communication signal is to be kept covert. Detecting the presence of stego is a very difficult problem which is made even more difficult when the embedding technique is not known. This article presents an investigation of the process and necessary considerations inherent in the development of a new method applied for the detection of hidden data within digital images. We demonstrate the effectiveness of learning vector quantization (LVQ) as a clustering technique which assists in discerning clean or non-stego images from anomalous or stego images. This comparison is conducted using 7 featuresover a small set of 200 observations with varying levels of embedded information from 1% to 10% in increments of 1%. The results demonstrate that LVQ not only more accurately identify when an image contains LSB hidden information when compared to k-means or using just the raw feature sets, but also provides a simple method for determining the percentage of embedding given low information embedding percentages.

Transform domain information hiding has been an important field for several years. Recent parameterized methods have been introduced to expand the available key-space for information hiding techniques. This paper introduces and defines Visually Similar Wavelet systems. Visually Similar Wavelet systems are those pairs or sets of wavelets that preserve visually pleasing aspects of an image. The application of these techniques is discussed in the context of two different information hiding fields, watermarking and steganography. An example is presented illustrating the use in fragile watermarking.

This paper presents an enhancement technique based upon a new application of histograms on transform domain coefficients called logarithmic transform coefficient histogram shifting (LTHS). A measure of enhancement based on contrast entropy is used as a tool for evaluating the performance of the proposed enhancement technique and for finding optimal values for variables contained in the enhancement. The algorithm's performance is compared quantitatively to classical histogram equalization using the aforementioned measure of enhancement. Experimental results are presented to show the performance of the proposed algorithm alongside classical histogram equalization.

By thwarting visual and chi2attacks, the F5 steganographic algorithm is viewed as a challenge to steganalysis. This paper presents a novel algorithm that can break F5, even with low embedding rates. The test results show that the proposed method can accurately break F5 when relatively short messages (82 bytes) are embedded into a 256times256 gray image

A method of the vectorial representation for splitting the calculation of the nonseparable three-dimensional discrete Hartley transform (3D DHT) into a set of one-dimensional (1D) DHTs is presented. The method is based on the vectorial, or tensor form of representation of a 3D image and can be applied to any orders of the transform. The case of the N/spl times/N&N-point DHT, for N=2/sup r/ (r>1), is considered in detail. The number of multiplications required for calculating the 3D DHT by the method of vectorial representation equals 7[8/sup r-1/(r-3)+4/sup r-1/] that is the best estimate of all existent algorithms. The improvement of this method, the recurrent algorithm, that reduces about 1.6 times the number of multiplications is also described.

This paper presents a novel accelerated predictive-transform (APT) modeling methodology for use in compression. The APT scheme is illustrated with a monochrome 2D image compression application yielding very promising results. For example, when the Lena image is compressed to 0.056 bits per pixel and the pixel blocks are of dimension 16×16, it is shown that both the design and implementation computational complexity of the prior predictive-transform (PT) modeling art is improved by a factor of 12 without any loss in the visual quality of the compressed image. The APT methodology can also be used in other application areas such as estimation; detection, identification, channel and source integrated coding, and control and other related areas.

In this letter, we propose a new construction method for a class of parametric Slant-Hadamard transforms that includes but is not limited to the commonly used Slant-Hadamard and Hadamard transforms. This parametric class performs better in generalized Wiener filtering than existing Slant-Hadamard transforms for the first-order Markov and the generalized image correlation models. We also show that the new parametric Slant-Hadamard transform outperforms the commonly used discrete cosine transform for the generalized image correlation model.

This paper presents a new class of the "frequency domain"-based signal/image enhancement algorithms including magnitude reduction, log-magnitude reduction, iterative magnitude and a log-reduction zonal magnitude technique. These algorithms are described and applied for detection and visualization of objects within an image. The new technique is based on the so-called sequency ordered orthogonal transforms, which include the well-known Fourier, Hartley, cosine, and Hadamard transforms, as well as new enhancement parametric operators. A wide range of image characteristics can be obtained from a single transform, by varying the parameters of the operators. We also introduce a quantifying method to measure signal/image enhancement called EME. This helps choose the best parameters and transform for each enhancement. A number of experimental results are presented to illustrate the performance of the proposed algorithms.

At low bit rates, the linear subband coders are susceptible to the ringing effect, which causes rippling and blurring around the edges in the images. On the other hand, the nonlinear coders are affected by the smearing effect wherein the detail regions are removed. In this paper, we introduce fuzzy subband coding system. This system uses fuzzy median filters in the analysis and synthesis stage of the coder. The motivation for this study is to determine if this novel system can reduce both ringing and smearing effect. Experimental results show that this new subband coder does out-perform linear and median filter subband coders, both in PSNR and visually.

In this paper, three algorithms based on the method of vector and paired transforms for dividing the computation of the nonseparable two-dimensional discrete Hartley transform (2-D DHT) into the "minimal" number of the one-dimensional (1-D) DHT's are presented. The computational complexity of the proposed method is analyzed, and the comparative estimates revealing the efficiency of the proposed algorithms with respect to the known algorithms are given.