An Object-Distortion Based Image Quality Similarity

Abstract

Image quality assessment (IQA) aims to devise perceptual models to predict the image quality consistently with human subjective evaluation. The representative metrics focus on measuring the image quality with low-level features. In this letter, we assumed that the distortion in specific regions containing semantically significant objects would be enhanced by HVS significantly. According to this hypothesis, a novel IQA metric based on a commonly used object-detecting feature, Speed Up Robust Features (SURF), was proposed. First, it determined the interest points which represented significant objects through the SURF features both on the reference image and distorted image. Then it computed the multilevel SURF descriptors differences between the reference image and the distorted one. Finally, all the difference results were combined with a suitable pooling strategy. Comparing with other nine state-of-the-art IQA models on three biggest IQA databases, SURF-SIM demonstrated its highly competitive prediction accuracy especially on complicated applications and excellent robustness across different distortion types.