Convex Optimization Method for Quantifying Image Quality Induced Saliency Variation

Visual saliency plays a significant role in image quality assessment. Image distortions cause shift of from its original places. Being able to measure such distortion-included variation (DSV) contributes towards the optimal use automated In our previous study benchmark for measurement DSV through subjective testing was built. However, exiting similarity measures are unhelpful quantification due fact that highly depends on dispersion degree map. this paper, we propose novel metric DSV, namely MDSV, based convex optimization method. The proposed MDSV integrates local and global using function as modulator. We detail parameter selection interactions sub-models strategy. Statistical analyses show outperforms existing metrics quantifying induced variation.