Endoscopy is one of the most commonly used tools for gastrointestinal examination. However, due to its close dependence on the experience of operators, the missed diagnosis rate of early gastric cancer (EGC) is still high. Therefore, the auxiliary detection of EGC based on endoscopic images is of great significance. In order to better fuse low-level features with rich details and high-level features with sufficient semantics, in this paper, we propose a deeper-shallower feature enhancement (DSF) module, in which the feature maps from both deeper layer and shallower layer are combined to enhance the features of current layer. Then the enhanced features are used as the next shallower input in the bottom-up path feature fusion (BUF) module, which transmits the enhanced features in a bottom-up manner. In order to capture features that focus more on accurate information, the channel-wise attention (CA) module is applied before prediction. Moreover, an endoscopic image dataset that contains four categories of lesions is established for implementing the task of EGC detection. Experimentally, the proposed method achieves the fl-scores of 90.65%, 63.34% and 89.95% on Kvasir dataset, ETIS-Larib dataset and our endoscopic dataset respectively, outperforming the baseline by 0.62%, 3.14% and 2.03% respectively.

Cross-modal retrieval aims to enable flexible retrieval experience by combining multimedia data such as image, video, text, and audio. One core of unsupervised approaches is to dig the correlations among different object representations to complete satisfied retrieval performance without requiring expensive labels. In this paper, we propose a Graph Pattern Loss based Diversified Attention Network (GPLDAN) for unsupervised cross-modal retrieval to deeply analyze correlations among representations. First, we propose a diversified attention feature projector by considering the interaction between different representations to generate multiple representations of an instance. Then, we design a novel graph pattern loss to explore the correlations among different representations, in this graph all possible distances between different representations are considered. In addition, a modality classifier is added to explicitly declare the corresponding modalities of features before fusion and guide the network to enhance discrimination ability. We test GPLDAN on four public datasets. Compared with the state-of-the-art cross-modal retrieval methods, the experimental results demonstrate the performance and competitiveness of GPLDAN.

The detection of built-up areas is essential for high-resolution Synthetic Aperture Rader (SAR) applications, such as urban planning and environmental monitoring. In this paper, we proposed an attention based convolutional neural network for the detection of built-up areas in SAR images. Our network composes of two parts. First part contains two branches, one is designed to obtain high detection rate and the other one is designed to obtain low false alarm rate. Second part aims to merge the advantages of the two detection results of first part by using attention mechanism. Experiments on TerraSAR-X high resolution SAR images over Beijing demonstrate the effectiveness of proposed method.

In this paper, we propose a novel method with comprehensive distance-preserving autoencoders (CDPAE) to address the problem of unsupervised cross-modal retrieval. Previous unsupervised methods rely primarily on pairwise distances of representations extracted from cross media spaces that co-occur and belong to the same objects. However, besides pairwise distances, the CDPAE also considers heterogeneous distances of representations extracted from cross media spaces as well as homogeneous distances of representations extracted from single media spaces that belong to different objects. The CDPAE consists of four components. First, denoising autoencoders are used to retain the information from the representations and to reduce the negative influence of redundant noises. Second, a comprehensive distance-preserving common space is proposed to explore the correlations among different representations. This aims to preserve the respective distances between the representations within the common space so that they are consistent with the distances in their original media spaces. Third, a novel joint loss function is defined to simultaneously calculate the reconstruction loss of the denoising autoencoders and the correlation loss of the comprehensive distance-preserving common space. Finally, an unsupervised cross-modal similarity measurement is proposed to further improve the retrieval performance. This is carried out by calculating the marginal probability of two media objects based on a kNN classifier. The CDPAE is tested on four public datasets with two cross-modal retrieval tasks: "query images by texts" and "query texts by images". Compared with eight state-of-the-art cross-modal retrieval methods, the experimental results demonstrate that the CDPAE outperforms all the unsupervised methods and performs competitively with the supervised methods.

The problem of model order selection from signed measurements obtained via 1-bit sampling is considered. The extension of the Bayesian information criterion (BIC) to the case of 1-bit sampling, referred to as 1bBIC, is proposed to determine the signal model order. A detailed analysis of and an application to sinusoidal signals are presented to demonstrate the performance of 1bBIC when the One-Bit RELAX algorithm is used to estimate the parameters of sinusoidal signals.

Gradients are commonly used in image sharpness assessment methods. However, research has not fully addressed the direct relationship between gradients and the perceived sharpness. In this paper, we discover and validate through experiments that the maximum gradient is an effective indicator of the perceived image sharpness on a global or local scale. Based on these observations, we propose a novel and efficient no-reference image quality assessment (NR-IQA) method for blurry images. Our method uses two elements to predict the quality of blurry images: the maximum gradient and the variability of gradients. The maximum gradient represents the sharpest spot in an image, and the variability of gradients shows variations within the content of the image. According to the characteristics of human visual systems, these factors are significant for humans when judging the quality of blurry images. The method was tested using blurry image datasets from five public IQA databases. Compared with nine other state-of-the-art NR-IQA methods for blurry images, the experimental results demonstrate that our method is more consistent with humans' subjective evaluations. The MATLAB source code of our method is available at https://github.com/Atmegal/Sharpness-evaluation.

Text-based CAPTCHA as a security technology is used widely to distinguish human beings from computer programs. Compared with the classification of sub-image containing individual character, segmentation is the key to standard approaches to solving CAPTCHAs automatically. However, the effectiveness of the traditional approaches is limited when the characters in CAPTCHAs are connected and distorted. In this paper, we propose a novel approach to solving CAPTCHAs without segmentation via using a multi-label convolutional neural network. The design of the network refers to the procedure that humans recognize CAPTCHAs containing connected characters and learn the correlation between neighboring characters. Our approach archives high accuracy on various datasets of CAPTCHAs with sophisticated distortion and segmentation-resistance.

When scoring the quality of JPEG images, the two main considerations for viewers are blocking artifacts and improper luminance changes, such as blur. In this letter, we first propose two measures to estimate the blockiness and the luminance change within individual blocks. Then, a no-reference image quality assessment (NR-IQA) method for JPEG images is proposed. Our method obtains the quality score by considering the blocking artifacts and the luminance changes from all nonoverlapping 8 × 8 blocks in one JPEG image. The proposed method has been tested on five public IQA databases and compared with five state-of-the-art NR-IQA methods for JPEG images. The experimental results show that our method is more consistent with subjective evaluations than the state-of-the-art NR-IQA methods. The MATLAB source code of our method is available at http://image.ustc.edu.cn/IQA.html.

Structural information is critical for image quality assessment (IQA). In this paper, first, we propose a novel model of structural variations in images. The proposed model classifies the types of structural variation within images into four categories: slight deformations, additive impairments, detail losses, and confusing contents. This system of classification applies to most types of structural variations observed in practice. In this model, each pixel from the distorted images is classified according to its structural variation using fuzzy logic based on a set of structural features extracted from the images. Then, a novel IQA method based on these pixel classifications is proposed. This proposed method evaluates the image quality by combining two aspects: the distribution of different structural variations and the degree of structural differences. We test the proposed method using seven public databases. The experimental results indicate that our method is more consistent with the results of the subjective evaluation than were the nine other state-of-the-art IQA methods. The MATLAB source code of our method is available at http://image.ustc.edu.cn/IQA.html.

In this paper, we propose a new standard haze image database with nearly all kinds of haze situations. Our database includes haze-free images as well as different levels and situations of haze images, such as snowy and extremely serious haze images. Our database also records the related weather and air quality information. Moreover, the database offers a mean opinion score (MOS) for each image as the subjective evaluation of the haze severity. Our database provides ample haze images with various objective and subjective descriptions, and has significantly potential scientific value. Since haze is a reason leading to the degradation of the image quality, obtaining the quality of haze images is also necessary and meaningful. In this paper, a novel no-reference image quality assessment (IQA) method for haze images is also proposed. Our method analyzes the model of haze images to evaluate the quality. The experimental results on the haze database show that our method is consistent with the subjective evaluation.

Structural information is critical in image quality assessment (IQA). Although existing objective IQA methods have achieved high consistency with subjective perception, detecting structural variation remains a difficult task. In this paper, we propose a novel structural variation detection strategy that is based on binary logic and inspired by the bag-of-words model. The proposed strategy detects structural variation by comparing the occurrences of structural features within the original and distorted images. In order to show the effectiveness of this strategy, this paper also proposes a novel and simple IQA method based on this strategy. The proposed method evaluates the image quality from two aspects: the structure distortion and the luminance distortion. The experimental results from four public databases show that the proposed method is highly congruous with subjective evaluation. The results also prove that the detection strategy is useful.

In this paper, we find that the structure variance of images could be divided into four classifications, slight deformations, additive impairments, detail losses, and confusing contents, and what's more, for each classification, subjective evaluation is different. According this, we propose a novel image quality assessment (IQA) method based on structure variance classification. The proposed method classifies the structure variance of each patch into one of the four classifications using binary logic and then summarizes the areas of different classifications. To get more comprehensive evaluation, the proposed method also incorporates the measurements of differences between extracted features. Our method is tested on five public databases and compared with seven state-of-art methods. The experimental results demonstrate that our method can achieve higher consistency in relation to the subjective evaluation compared to the state-of-art IQA methods.

Multi-channel peculiarity is one of the most widely accepted human visual system (HVS) models for perceptual image quality assessment (IQA). Otherwise than extensive studies of channel decomposition and intra-channel distortion measure, relatively scant research effort has been devoted to develop efficient multichannel evaluation pooling strategies. In this paper, we review and address the limitations of the conventional pooling models based on HVS sensitivities-weighted average. Instead, we explore the utilization of machine learning for this pooling problem, since machine learning can establish an optimal and generalized mapping that models the highly complex relationship between the multi-channel distortion evaluations and the perceived image quality. Experiments based on available subjective IQA databases demonstrate the rationality, reliability and robustness of our proposed scheme.

In this paper, we propose a novel remote sensing image compression method based on double-sparsity dictionary learning and universal trellis coded quantization (UTCQ). Recent years have seen a growing interest in the study of natural image compression based on sparse representation and dictionary learning. We show that using the double-sparsity model to learn a dictionary gives much better compression results for remote sensing images, the texture of which is much richer than that of natural images. We also show that the compression performance is improved significantly when advanced quantization and entropy coding strategies are used for encoding the sparse representation coefficients. The proposed method outperforms the existing dictionary-based image coding algorithms. Additionally, our method results in better ratedistortion performance and structural similarity results than CCSDS and JPEG2000 standard.

Due to that there are a large number of similar characteristics in surface structure of the SAR image, a novel SAR image compression algorithm was proposed based on 3D wavelet transform after block reordering. This proposed algorithm consists of four successive steps: divide the image into sub-blocks with equal size, reorder the sub-blocks according to the similarity measured by weighted Euclidean distance to form 3D array, then 3D wavelet transform and 3D-SPIHT coding are employed for encoding. Experimental results of real SAR images show that the proposed method outperforms the traditional wavelet-based SPIHT in terms of PSNR, especially at the low-bit rate.

Objective image quality assessment (QA) is a fundamental and challenging job in image processing which evaluates the image quality consistently with human perception automatically. Generally, an image can be segmented into two kinds of areas: structure and texture. And structural information plays a much more important role between the two. The pixels, edges and shape with directional characteristic contribute much more to the structural information. In this paper, the structural information is modeled as the energy of directional projection, which is shown in a directional projection-based map that is built by Radon transform. On the assumption that any image's distortion could be modeled as the difference between the directional projection-based maps of reference and distortion images, we propose a new objective quality assessment method with Radon transform for full reference model, and we also try to explore the feasibility to develop the image QA metrics with scalable efficiency and computational cost. Experimental results show that the proposed metrics are well consistent with the subjective quality score.

Valuation of image coding relies on not only the efficiency of the coding, but also the quality of the coded image. We present a new objective quality assessment metric for image coding based on matching pursuit. First of all, we get the characteristics of the most important structure by projecting the reference image onto the base functions from a dictionary using matching pursuit. Secondly, we process the reference image and gain the structure information of the images in the order of importance, projecting the images onto the structural characteristics. Finally the objective quality score is given by comparing the differences of structure information between the reference and coded images. Experimental results show that the proposed approach is well consistent with the subjective quality score.

We propose a novel system for analyzing pedestrians' walking patterns by exploiting single-row laser range scanners that measure distances of surrounding objects by reflecting eye-safe laser beams. A walking model is built in the spatial-temporal domain to describe the periodicity of the movement of the feet, and a mean-shift technique is applied to recover model parameters. Compared with camera-based methods, our system provides a novel technique to analyze the behavior of pedestrians. The experiments show the validity of the algorithm.

A face recognition method based on the fusion of linear discriminant analysis (LDA) and singular value decomposition (SVD) is presented. In theory, fusion of different data or classifiers can achieve better performance when they are independent of each other or they can overcome shortcomings of each other. As one of the subspace methods, LDA-based method has a drawback that LDA is sensitive (variant) to translation, rotation and other geometric transforms. SVD-based method, as an algebraic feature extraction approach, has the merit of invariance to translation, rotation and mirror transforms. By combining these two methods, it is expected that better recognition performance can be obtained. Experiment results on ORL face database show the effectiveness of the proposed method.