Full-reference image quality assessment via region-based analysis
Ke Gu, Wenjun Zhang, Ci Wang, Guangtao Zhai · 2011
Image quality assessment (IQA) plays an important role in many image processing systems. Based on the fact that different image components have different visual impact, we propose a new region-based method using a three-region image model and Back Propagation (BP) neural network. Experimental results show that our algorithm is obviously better than the peer image quality assessment method, using the Laboratory for Image and Video Engineering (LIVE) database as a test-bed.