Abdul Rehman

Bio: Abdul Rehman is an academic researcher from University of Waterloo. The author has contributed to research in topics: Video quality & Image quality. The author has an hindex of 20, co-authored 30 publications receiving 1481 citations.

Reduced-Reference Image Quality Assessment by Structural Similarity Estimation

Abstract: Reduced-reference image quality assessment (RR-IQA) provides a practical solution for automatic image quality evaluations in various applications where only partial information about the original reference image is accessible. In this paper, we propose an RR-IQA method by estimating the structural similarity index (SSIM), which is a widely used full-reference (FR) image quality measure shown to be a good indicator of perceptual image quality. Specifically, we extract statistical features from a multiscale multiorientation divisive normalization transform and develop a distortion measure by following the philosophy in the construction of SSIM. We find an interesting linear relationship between the FR SSIM measure and our RR estimate when the image distortion type is fixed. A regression-by-discretization method is then applied to normalize our measure across image distortion types. We use six publicly available subject-rated databases to test the proposed RR-SSIM method, which shows strong correlations with both SSIM and subjective quality evaluations. Finally, we introduce the novel idea of partially repairing an image using RR features and use deblurring as an example to demonstrate its application.

SSIM-Motivated Rate-Distortion Optimization for Video Coding

Abstract: We propose a rate-distortion optimization (RDO) scheme based on the structural similarity (SSIM) index, which was found to be a better indicator of perceived image quality than mean-squared error, but has not been fully exploited in the context of image and video coding. At the frame level, an adaptive Lagrange multiplier selection method is proposed based on a novel reduced-reference statistical SSIM estimation algorithm and a rate model that combines the side information with the entropy of the transformed residuals. At the macroblock level, the Lagrange multiplier is further adjusted based on an information theoretical approach that takes into account both the motion information content and perceptual uncertainty of visual speed perception. Finally, the mode for H.264/AVC coding is selected by the SSIM index and the adjusted Lagrange multiplier. Extensive experiments show that the proposed scheme can achieve significantly better rate-SSIM performance and provide better visual quality than conventional RDO coding schemes.

A Quality-of-Experience Index for Streaming Video

Abstract: With the rapid growth of streaming media applications, there has been a strong demand of quality-of-experience (QoE) measurement and QoE-driven video delivery technologies. Most existing methods rely on bitrate and global statistics of stalling events for QoE prediction. This is problematic for two reasons. First, using the same bitrate to encode different video content results in drastically different presentation quality. Second, the interactions between video presentation quality and playback stalling experiences are not accounted for. In this work, we first build a streaming video database and carry out a subjective user study to investigate the human responses to the combined effect of video compression, initial buffering, and stalling. We then propose a novel QoE prediction approach named Streaming QoE Index that accounts for the instantaneous quality degradation due to perceptual video presentation impairment, the playback stalling events, and the instantaneous interactions between them. Experimental results show that the proposed model is in close agreement with subjective opinions and significantly outperforms existing QoE models. The proposed model provides a highly effective and efficient meanings for QoE prediction in video streaming services. 1

Quality Prediction of Asymmetrically Distorted Stereoscopic 3D Images

Abstract: Objective quality assessment of distorted stereoscopic images is a challenging problem, especially when the distortions in the left and right views are asymmetric. Existing studies suggest that simply averaging the quality of the left and right views well predicts the quality of symmetrically distorted stereoscopic images, but generates substantial prediction bias when applied to asymmetrically distorted stereoscopic images. In this paper, we first build a database that contains both single-view and symmetrically and asymmetrically distorted stereoscopic images. We then carry out a subjective test, where we find that the quality prediction bias of the asymmetrically distorted images could lean toward opposite directions (overestimate or underestimate), depending on the distortion types and levels. Our subjective test also suggests that eye dominance effect does not have strong impact on the visual quality decisions of stereoscopic images. Furthermore, we develop an information content and divisive normalization-based pooling scheme that improves upon structural similarity in estimating the quality of single-view images. Finally, we propose a binocular rivalry-inspired multi-scale model to predict the quality of stereoscopic images from that of the single-view images. Our results show that the proposed model, without explicitly identifying image distortion types, successfully eliminates the prediction bias, leading to significantly improved quality prediction of the stereoscopic images. 1 1 Some partial preliminary results of this work were presented at International Workshop on Video Processing and Quality Metrics for Consumer Electronics, Chandler, AZ, Jan., 2014. and IEEE International Conference on Multimedia and Expo, Chengdu, China, July, 2014.

Perceptual Video Coding Based on SSIM-Inspired Divisive Normalization

Abstract: We propose a perceptual video coding framework based on the divisive normalization scheme, which is found to be an effective approach to model the perceptual sensitivity of biological vision, but has not been fully exploited in the context of video coding. At the macroblock (MB) level, we derive the normalization factors based on the structural similarity (SSIM) index as an attempt to transform the discrete cosine transform domain frame residuals to a perceptually uniform space. We further develop an MB level perceptual mode selection scheme and a frame level global quantization matrix optimization method. Extensive simulations and subjective tests verify that, compared with the H.264/AVC video coding standard, the proposed method can achieve significant gain in terms of rate-SSIM performance and provide better visual quality.

Loss Functions for Image Restoration With Neural Networks

Abstract: Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems. The impact of the loss layer of neural networks, however, has not received much attention in the context of image processing: the default and virtually only choice is $\ell _2$ . In this paper, we bring attention to alternative choices for image restoration. In particular, we show the importance of perceptually-motivated losses when the resulting image is to be evaluated by a human observer. We compare the performance of several losses, and propose a novel, differentiable error function. We show that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged.

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

Abstract: 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.

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

Abstract: 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.

Using free energy principle for blind image quality assessment

Abstract: In this paper we propose a new no-reference (NR) image quality assessment (IQA) metric using the recently revealed free-energy-based brain theory and classical human visual system (HVS)-inspired features. The features used can be divided into three groups. The first involves the features inspired by the free energy principle and the structural degradation model. Furthermore, the free energy theory also reveals that the HVS always tries to infer the meaningful part from the visual stimuli. In terms of this finding, we first predict an image that the HVS perceives from a distorted image based on the free energy theory, then the second group of features is composed of some HVS-inspired features (such as structural information and gradient magnitude) computed using the distorted and predicted images. The third group of features quantifies the possible losses of “naturalness” in the distorted image by fitting the generalized Gaussian distribution to mean subtracted contrast normalized coefficients. After feature extraction, our algorithm utilizes the support vector machine based regression module to derive the overall quality score. Experiments on LIVE, TID2008, CSIQ, IVC, and Toyama databases confirm the effectiveness of our introduced NR IQA metric compared to the state-of-the-art.

Color image database TID2013: Peculiarities and preliminary results

Abstract: Visual quality of color images is an important aspect in various applications of digital image processing and multimedia. A large number of visual quality metrics (indices) has been proposed recently. In order to assess their reliability, several databases of color images with various sets of distortions have been exploited. Here we present a new database called TID2013 that contains a larger number of images. Compared to its predecessor TID2008, seven new types and one more level of distortions are included. The need for considering these new types of distortions is briefly described. Besides, preliminary results of experiments with a large number of volunteers for determining the mean opinion score (MOS) are presented. Spearman and Kendall rank order correlation factors between MOS and a set of popular metrics are calculated and presented. Their analysis shows that adequateness of the existing metrics is worth improving. Special attention is to be paid to accounting for color information and observers focus of attention to locally active areas in images.