A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
2006 Special Issue: Modeling attention to salient proto-objects
Neural Networks
Image quality assessment: from error visibility to structural similarity
IEEE Transactions on Image Processing
An information fidelity criterion for image quality assessment using natural scene statistics
IEEE Transactions on Image Processing
Image information and visual quality
IEEE Transactions on Image Processing
Hi-index | 0.00 |
Image quality assessment (IQA) is a critical issue in image processing applications, but traditional criteria based on the differences between reference and distorted images do not correlate well with perceived quality. MSSIM and VIF criteria proposed recently are regarded as excellent models in comparison with others, but they only consider local features and ignore some global concepts. In this paper, we propose an improved method that adds global saliency features to the criteria of MSSIM and VIF. For the sake of reducing the computational complexity, we propose a simpler and faster method to extract the saliency map. Experimental results for a set of intuitive examples as well as validation on a database of 779 images with different distortion types demonstrate that the improved IQA criteria can get a better performance than their original forms.