Full Reference Image Quality Assessment Algorithm based on Haar Wavelet and Edge Perceptual Similarity

Abstract

The research on image quality assessment (IQA) has been become a hot topic in image processing. Many studies show that HVS edge information plays crucial role when human perceive the quality of an image. The proposed metric is called HEPSI. The method from HaarPSI metric is combined with edge structural similarity and a contrast map is added for pooling the structural similarity map, Validation is taken by comparing HEPSI with the well-known state-of-the-art IQA metrics: PSNR, SSIM, MSSIM, FSIM and HaarPSI over the LIVE database. Experiment shows that HEPSI achieved better performance than other 5 IQA metrics.