Jiheng Wang

Quality Prediction of Asymmetrically Distorted Stereoscopic 3D Images

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.

Image classification based on complex wavelet structural similarity

Abstract Complex wavelet structural similarity (CW-SSIM) index has been recognized as a novel image similarity measure of broad potential applications due to its robustness to small geometric distortions such as translation, scaling and rotation of images. Nevertheless, how to make the best use of it in image classification problems has not been deeply investigated. In this paper, we introduce a series of novel image classification algorithms based on CW-SSIM and use handwritten digit recognition, and face recognition as examples for demonstration. Among the proposed approaches, the best compromise between accuracy and complexity is obtained by the CW-SSIM support vector machine based algorithms, which combines an unsupervised clustering method to divide the training images into clusters with representative images and a supervised learning method based on support vector machines to maximize the classification accuracy. Our experiments show that such a conceptually simple image classification method, which does not involve any registration, intensity normalization or sophisticated feature extraction processes, and does not rely on any modeling of the image patterns or distortion processes, achieves competitive performance with reduced computational cost.

Quality prediction of asymmetrically distorted stereoscopic images from single views

Objective quality assessment of distorted stereoscopic images is a challenging problem. 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 study, we first carry out a subjective test, where we find that the prediction bias could lean towards opposite directions, largely depending on the distortion types. We then develop an information-content and divisive normalization based pooling scheme that improves upon SSIM in estimating the quality of single view images. Finally, we propose a binocular rivalry inspired model to predict the quality of stereoscopic images based on 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 stereoscopic images.

Perceptual Depth Quality in Distorted Stereoscopic Images

Subjective and objective measurement of the perceptual quality of depth information in symmetrically and asymmetrically distorted stereoscopic images is a fundamentally important issue in stereoscopic 3D imaging that has not been deeply investigated. Here, we first carry out a subjective test following the traditional absolute category rating protocol widely used in general image quality assessment research. We find this approach problematic, because monocular cues and the spatial quality of images have strong impact on the depth quality scores given by subjects, making it difficult to single out the actual contributions of stereoscopic cues in depth perception. To overcome this problem, we carry out a novel subjective study where depth effect is synthesized at different depth levels before various types and levels of symmetric and asymmetric distortions are applied. Instead of following the traditional approach, we ask subjects to identify and label depth polarizations, and a depth perception difficulty index (DPDI) is developed based on the percentage of correct and incorrect subject judgements. We find this approach highly effective at quantifying depth perception induced by stereo cues and observe a number of interesting effects regarding image content dependency, distortion-type dependence, and the impact of symmetric versus asymmetric distortions. Furthermore, we propose a novel computational model for DPDI prediction. Our results show that the proposed model, without explicitly identifying image distortion types, leads to highly promising DPDI prediction performance. We believe that these are useful steps toward building a comprehensive understanding on 3D quality-of-experience of stereoscopic images.

Quality prediction of asymmetrically compressed stereoscopic videos

Objective quality assessment of stereoscopic 3D video is a challenging problem. We carry out a subjective test on symmetrically and asymmetrically compressed stereoscopic videos followed by different levels of low-pass filtering. We observe a strong systematic bias when using direct averaging of 2D video quality of both views to predict 3D video quality. We use a binocular rivalry inspired model to account for the prediction bias, leading to significantly improved quality estimation of stereoscopic videos. The model allows us to quantitatively predict the potential coding gain of asymmetric video compression, and provides new insight on the development of high efficiency 3D video coding schemes.

SSIM-Based Coarse-Grain Scalable Video Coding

We propose an improved coarse-grain scalable video coding (SVC) approach based on the structural similarity (SSIM) index as the visual quality criterion, aiming at maximizing the overall coding performance constrained by user-defined quality weightings for all scalable layers. First, we develop an interlayer rate-SSIM dependency model, by investigating bit rate and SSIM relationships between different layers. Second, a reduced-reference SSIM-Q model and a Laplacian R-Q model are introduced for SVC, by incorporating the characteristics of hierarchical prediction structure in each layer. Third, based on the user-defined weightings and the proposed models, we design a rate-distortion optimization approach to adaptively adjust Lagrange multipliers for all layers to maximize the overall rate-SSIM performance of the scalable encoder. Experiments with multiple layers, different layer weightings, and various videos demonstrate that the proposed framework can achieve better rate-SSIM performance than single layer optimization method, and provide better coding efficiency as compared to the conventional SVC scheme. Subjective tests further demonstrate the benefits of the proposed scheme.

Asymmetrically Compressed Stereoscopic 3D Videos: Quality Assessment and Rate-Distortion Performance Evaluation

Objective quality assessment of stereoscopic 3D video is challenging but highly desirable, especially in the application of stereoscopic video compression and transmission, where useful quality models are missing, that can guide the critical decision making steps in the selection of mixed-resolution coding, asymmetric quantization, and pre- and post-processing schemes. Here we first carry out subjective quality assessment experiments on two databases that contain various asymmetrically compressed stereoscopic 3D videos obtained from mixed-resolution coding, asymmetric transform-domain quantization coding, their combinations, and the multiple choices of postprocessing techniques. We compare these asymmetric stereoscopic video coding schemes with symmetric coding methods and verify their potential coding gains. We observe a strong systematic bias when using direct averaging of 2D video quality of both views to predict 3D video quality. We then apply a binocular rivalry inspired model to account for the prediction bias, leading to a significantly improved full reference quality prediction model of stereoscopic videos. The model allows us to quantitatively predict the coding gain of different variations of asymmetric video compression, and provides new insight on the development of high efficiency 3D video coding schemes.

CW-SSIM kernel based random forest for image classification

Complex wavelet structural similarity (CW-SSIM) index has been proposed as a powerful image similarity metric that is robust to translation, scaling and rotation of images, but how to employ it in image classification applications has not been deeply investigated. In this paper, we incorporate CW-SSIM as a kernel function into a random forest learning algorithm. This leads to a novel image classification approach that does not require a feature extraction or dimension reduction stage at the front end. We use hand-written digit recognition as an example to demonstrate our algorithm. We compare the performance of the proposed approach with random forest learning based on other kernels, including the widely adopted Gaussian and the inner product kernels. Empirical evidences show that the proposed method is superior in its classification power. We also compared our proposed approach with the direct random forest method without kernel and the popular kernel-learning method support vector machine. Our test results based on both simulated and realworld data suggest that the proposed approach works superior to traditional methods without the feature selection procedure.

Comparison of dual energy subtraction chest radiography and traditional chest X-rays in the detection of pulmonary nodules

BACKGROUND Dual energy subtraction (DES) radiography is a powerful but underutilized technique which aims to improve the diagnostic value of an X-ray by separating soft tissue from bones, producing two different images. Compared to traditional chest X-rays, DES requires exposure to higher doses of radiation but may achieve higher accuracy. The objective of this study was to assess the clinical benefits of DES radiography by comparing the speed and accuracy of diagnosis of pulmonary nodules with DES versus traditional chest X-rays. METHODS Five radiologists and five radiology residents read the DES and traditional chest X-rays of 51 patients, 34 with pulmonary nodules and 17 without. Their accuracy and speed in the detection of nodules were measured using specialized image display software. RESULTS DES radiography reduced reading time from 13 to 10 sec (P<0.0001) in staff and from 21 to 15 sec in residents (P<0.0001). There was also a small increase in sensitivity 0.58 to 0.67 overall (P<0.10) with no change in specificity (0.85 overall). CONCLUSIONS By eliminating rib shadows in soft tissue images, DES improved the speed and accuracy of radiologists in the diagnosis of pulmonary nodules.

Perceptual quality assessment of high frame rate video

High frame rate video has been a hot topic in the past few years driven by a strong need in the entertainment and gaming industry. Nevertheless, progress on perceptual quality assessment of high frame rate video remains limited, making it difficult to evaluate the exact perceptual gain by switching from low to high frame rates. In this work, we first conduct a subjective quality assessment experiment on a database that contains videos compressed at different frame rates, quantization levels and spatial resolutions. We then carry out a series of analysis on the subjective data to investigate the impact of frame rate on perceived video quality and its interplay with quantization level, spatial resolution, spatial complexity, and motion complexity. We observe that perceived video quality generally increases with frame rate, but the gain saturates at high rates. Such gain also depends on the interactions between quantization level, spatial resolution, and spatial and motion complexities.