Abstract
Video quality assessment (VQA) plays an important role in video applications for quality evaluation and resource allocation. It aims to evaluate video quality in a way that is consistent with human perception. In this letter, a hierarchical gradient similarity based VQA metric is proposed inspired by the structure of the primate visual cortex, in which visual information is processed through sequential visual areas. These areas are modeled with the corresponding measures to evaluate the overall perceptual quality. Experimental results on the LIVE database show that the proposed VQA metric significantly outperforms most of the state-of-the-art VQA metrics.
Highlights
Video quality assessment (VQA) metrics which can evaluate the video quality consistent with the human perception have received increased attention
The effectiveness of the proposed VQA metrics is evaluated by the consistency between the objective scores and the subjective scores, including Mean Opinion Score (MOS) and Difference Mean Opinion Score (DMOS)
The consistency is measured by the Pearson correlation coefficient (PCC) and the Spearman rank order correlation coefficient (SROCC)
Summary
Video quality assessment (VQA) metrics which can evaluate the video quality consistent with the human perception have received increased attention. Peak signal-to-noise ratio (PSNR) and Mean square error (MSE) [1,2] are the most widely used FR metrics These indices are simple to calculate and can be conveniently adopted in video and image applications, such as image processing and video coding [3,4,5]. SSIM-based VQA metrics have been proposed by introducing motion information, temporal weighting schemes, and multi-scales-based schemes [8,9,10] These metrics are developed based on the assumption that the degradation of perceptual qualities is highly related to the change of the structural information. A VQA metric is designed based on a hierarchical gradient similarity model This model is inspired by functional principles of the processing hierarchies in the primate visual system [14], which is characterized by a sequence of visual areas. Experimental results show that the proposed VQA metric outperforms the state-of-the-art VQA metrics
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.