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-bas...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.展开更多
文摘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.
