SWVFS： a saliency weighted visual feature similarity metric for image quality assessment

作     者：Li CUI 

作者机构：School of Electronics and Information Northwestern Polytechnical University Xi'an 710072 China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2014年第8卷第1期

页      面：145-155页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：国家自然科学基金 国家教育部高等学校博士学科点专项科研基金 Overseas Returnees Start-up Research Fund by Chinese Eduction Ministry 

主　　题：image quality assessment gradient texture vi-sual saliency 

摘      要：In this paper, a saliency weighted visual feature similarity （SWVFS） metric is proposed for full reference im- age quality assessment （IQA）. Instead of traditional spatial pooling strategies, a visual saliency-based approach is em- ployed for better compliance with properties of the human visual system, where the saliency allocation is closely related to the activity of posterior parietal cortex and the pluvial nu- clei of the thalamus. Assuming that the saliency map actually represents the contribution of locally computed visual distor- tions to the overall image quality, the gradient similarity and the textural congruency are merged into the final image qual- ity indicator. The gradient and texture comparison play com- plementary roles in characterizing the local image distortion. Extensive experiments conducted on seven publicly available image databases show that the performance of SWVFS is competitive with the state-of-the-art IQA algorithms.