Recent Advances and Challenges of Visual Signal Quality Assessment

While quality assessment is essential for testing, optimizing, benchmarking, monitoring, and inspecting related systems and services, it also plays an essential role in the design of virtually all visual signal processing and communication algorithms, as well as various related decision-making processes. In this paper, we first provide an overview of recently derived quality assessment approaches for traditional visual signals (i.e., 2D images/videos), with highlights for new trends (such as machine learning approaches). On the other hand, with the ongoing development of devices and multimedia services, newly emerged visual signals (e.g., mobile/3D videos) are becoming more and more popular. This work focuses on recent progresses of quality metrics, which have been reviewed for the newly emerged forms of visual signals, which include scalable and mobile videos, High Dynamic Range (HDR) images, image segmentation results, 3D images/videos, and retargeted images.

Proposal for Generation of the Three-Way Perceptual Map Using Non-metric Multidimensional Scaling with Clusters

The generation of a perceptual map via three-way multidimensional scaling allows analysts to see the separation of objects in Euclidean space. The MDSvarext method incorporates the objects＇ confidence regions in this analysis, allowing for statistical inference in the difference between objects, but the confidence regions that are generated are very large because of the inherent variability among the evaluators. One solution to this problem is cluster generation prior to the application of the MDSvarext method in order to obtain homogeneous subgroups and to achieve greater control of the variance. This work is relevant to studies of perception which usually evaluate the difference between objects or stimuli in the point of view of different people that judge this difference using several dimensions. This study investigated the possibility of using a K-means algorithm to generate subgroups before the MDSvarext method was applied, evaluating the process with two quality indicators, one Ex-Ante and one Ex-Post. The experiments were conducted based on simulation of judgment matrix of different objects in multiple dimensions being evaluated by several judges. In this experiment, the matrix used was a 10 objects, in 10 features, judged by 10 people. The results are promising as possible interpretations of the perceptual map and the indicators generated.

No-reference image quality assessment based on nonsubsample shearlet transform and natural scene statistics

A novel no-reference(NR) image quality assessment(IQA) method is proposed for assessing image quality across multifarious distortion categories. The new method transforms distorted images into the shearlet domain using a non-subsample shearlet transform(NSST), and designs the image quality feature vector to describe images utilizing natural scenes statistical features: coefficient distribution, energy distribution and structural correlation(SC) across orientations and scales. The final image quality is achieved from distortion classification and regression models trained by a support vector machine(SVM). The experimental results on the LIVE2 IQA database indicate that the method can assess image quality effectively, and the extracted features are susceptive to the category and severity of distortion. Furthermore, our proposed method is database independent and has a higher correlation rate and lower root mean squared error(RMSE) with human perception than other high performance NR IQA methods.