Xuanqin Mou

Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index

It is an important task to faithfully evaluate the perceptual quality of output images in many applications, such as image compression, image restoration, and multimedia streaming. A good image quality assessment (IQA) model should not only deliver high quality prediction accuracy, but also be computationally efficient. The efficiency of IQA metrics is becoming particularly important due to the increasing proliferation of high-volume visual data in high-speed networks. We present a new effective and efficient IQA model, called gradient magnitude similarity deviation (GMSD). The image gradients are sensitive to image distortions, while different local structures in a distorted image suffer different degrees of degradations. This motivates us to explore the use of global variation of gradient based local quality map for overall image quality prediction. We find that the pixel-wise gradient magnitude similarity (GMS) between the reference and distorted images combined with a novel pooling strategy-the standard deviation of the GMS map-can predict accurately perceptual image quality. The resulting GMSD algorithm is much faster than most state-of-the-art IQA methods, and delivers highly competitive prediction accuracy. MATLAB source code of GMSD can be downloaded at http://www4.comp.polyu.edu.hk/~cslzhang/IQA/GMSD/GMSD.htm.

Low-Dose X-ray CT Reconstruction via Dictionary Learning

Although diagnostic medical imaging provides enormous benefits in the early detection and accuracy diagnosis of various diseases, there are growing concerns on the potential side effect of radiation induced genetic, cancerous and other diseases. How to reduce radiation dose while maintaining the diagnostic performance is a major challenge in the computed tomography (CT) field. Inspired by the compressive sensing theory, the sparse constraint in terms of total variation (TV) minimization has already led to promising results for low-dose CT reconstruction. Compared to the discrete gradient transform used in the TV method, dictionary learning is proven to be an effective way for sparse representation. On the other hand, it is important to consider the statistical property of projection data in the low-dose CT case. Recently, we have developed a dictionary learning based approach for low-dose X-ray CT. In this paper, we present this method in detail and evaluate it in experiments. In our method, the sparse constraint in terms of a redundant dictionary is incorporated into an objective function in a statistical iterative reconstruction framework. The dictionary can be either predetermined before an image reconstruction task or adaptively defined during the reconstruction process. An alternating minimization scheme is developed to minimize the objective function. Our approach is evaluated with low-dose X-ray projections collected in animal and human CT studies, and the improvement associated with dictionary learning is quantified relative to filtered backprojection and TV-based reconstructions. The results show that the proposed approach might produce better images with lower noise and more detailed structural features in our selected cases. However, there is no proof that this is true for all kinds of structures.

On the Dynamical Degradation of Digital Piecewise Linear Chaotic Maps

When chaotic systems are realized with finite precisions in digital computers, their dynamical properties are often found to be entirely different from the original versions in the continuous setting. In the literature, there does not seem to be much work on quantitative analysis of such degradation of digitized chaos and how to reduce its negative influence on chaos-based digital systems. Focusing on 1D piecewise linear chaotic maps (PWLCM), this paper reports some findings on a new series of dynamical indicators, which can quantitatively reflect the degradation effects on a digital PWLCM realized with a fixed-point finite precision. On top of that, the paper introduces a new method for studying digital chaos from an algorithmic point of view. In addition, the theoretical results obtained in this paper should be very helpful for the consideration of reducing negative influence of dynamical degradation in real design of various digital chaotic systems. As typical examples, the proposed dynamical indicators are applied to the performance comparison of different remedies for improving dynamical degradation, cryptanalysis of digital chaotic ciphers based on 1D PWLCM, and design of chaotic pseudo-random number generators with desired characteristics.

Learning without Human Scores for Blind Image Quality Assessment

General purpose blind image quality assessment (BIQA) has been recently attracting significant attention in the fields of image processing, vision and machine learning. State-of-the-art BIQA methods usually learn to evaluate the image quality by regression from human subjective scores of the training samples. However, these methods need a large number of human scored images for training, and lack an explicit explanation of how the image quality is affected by image local features. An interesting question is then: can we learn for effective BIQA without using human scored images? This paper makes a good effort to answer this question. We partition the distorted images into overlapped patches, and use a percentile pooling strategy to estimate the local quality of each patch. Then a quality-aware clustering (QAC) method is proposed to learn a set of centroids on each quality level. These centroids are then used as a codebook to infer the quality of each patch in a given image, and subsequently a perceptual quality score of the whole image can be obtained. The proposed QAC based BIQA method is simple yet effective. It not only has comparable accuracy to those methods using human scored images in learning, but also has merits such as high linearity to human perception of image quality, real-time implementation and availability of image local quality map.

On the security of a chaotic encryption scheme: problems with computerized chaos in finite computing precision

Zhou et al. have proposed a chaotic encryption scheme, which is based on a kind of computerized piecewise linear chaotic map (PWLCM) realized in finite computing precision. In this paper, we point out that Zhous encryption scheme is not secure enough from strict cryptographic viewpoint. The reason lies in the dynamical degradation of the computerized piecewise linear chaotic map employed by Zhou et al. The dynamical degradation of the computerized chaos induces many weak keys to cause large information leaking of the plaintext. In addition, we also discuss three simple countermeasures to enhance the security of Zhous cryptosystem, but none of them can essentially enhance the security.

Blind image quality assessment using joint statistics of gradient magnitude and laplacian features

Blind image quality assessment (BIQA) aims to evaluate the perceptual quality of a distorted image without information regarding its reference image. Existing BIQA models usually predict the image quality by analyzing the image statistics in some transformed domain, e.g., in the discrete cosine transform domain or wavelet domain. Though great progress has been made in recent years, BIQA is still a very challenging task due to the lack of a reference image. Considering that image local contrast features convey important structural information that is closely related to image perceptual quality, we propose a novel BIQA model that utilizes the joint statistics of two types of commonly used local contrast features: 1) the gradient magnitude (GM) map and 2) the Laplacian of Gaussian (LOG) response. We employ an adaptive procedure to jointly normalize the GM and LOG features, and show that the joint statistics of normalized GM and LOG features have desirable properties for the BIQA task. The proposed model is extensively evaluated on three large-scale benchmark databases, and shown to deliver highly competitive performance with state-of-the-art BIQA models, as well as with some well-known full reference image quality assessment models.

Chaotic encryption scheme for real-time digital video

In this paper, we propose a novel video encryption scheme based on multiple digital chaotic systems, which is called CVES (Chaotic Video Encryption Scheme). CVES is independent of any video compression algorithms, and can provide high security for real-time digital video with fast encryption speed, and can be simply realized both by hardware and software. Whatí»s more, CVES can be extended to support random retrieval of cipher-video with considerable maximal time-out; the extended CVES is called RRS-CVES (Random-Retrieval-Supported CVES). Essentially speaking, CVES is a universal fast encryption system and can be easily extended to other real-time applications. In CVES, 2n chaotic maps are used to generate pseudo-random signal to mask the video, and to make pseudo-random permutation of the masked video. Another single chaotic map is employed to initialize and control the above 2n chaotic maps. Detailed discussions are given to estimate the performance of CVES/RRS-CVES, respectively from the viewpoints of speed, security, realization and experiments.

Improving security of a chaotic encryption approach

E. Alvarez et al. presented a new chaotic encryption approach recently. But soon G. Alvarez et al. broke it with four cryptanalytic methods and found some other weaknesses. In this Letter we point out why the original scheme is so vulnerable to the proposed four attacks. The chief reasons are two essential defects existing in the original scheme. Based on such a fact, we present an improved encryption scheme to obtain higher security. The cryptographic properties of the improved scheme are studied theoretically and experimentally in detail.

Hierarchical multiscale LBP for face and palmprint recognition

Local binary pattern (LBP), fast and simple for implementation, has shown its superiority in face and palmprint recognition. To extract representative features, “uniform” LBP was proposed and its effectiveness has been validated. However, all “non-uniform” patterns are clustered into one pattern, so a lot of useful information is lost. In this study, the authors propose to build a hierarchical multiscale LBP histogram for an image. The useful information of “non-uniform” patterns at large scale is dug out from its counterpart of small scale. The main advantage of the proposed scheme is that it can fully utilize LBP information while it does not need any training step, which may be sensitive to training samples. Experiments on one public face database and one palmprint database show the effectiveness of the proposed method.

RFSIM: A feature based image quality assessment metric using Riesz transforms

Image quality assessment (IQA) aims to provide computational models to measure the image quality in a perceptually consistent manner. In this paper, a novel feature based IQA model, namely Riesz-transform based Feature SIMilarity metric (RFSIM), is proposed based on the fact that the human vision system (HVS) perceives an image mainly according to its low-level features. The 1st-order and 2nd-order Riesz transform coefficients of the image are taken as image features, while a feature mask is defined as the edge locations of the image. The similarity index between the reference and distorted images is measured by comparing the two feature maps at key locations marked by the feature mask. Extensive experiments on the comprehensive TID2008 database indicate that the proposed RFSIM metric is more consistent with the subjective evaluation than all the other competing methods evaluated.