Robust Blind Blur Identification Method Based on the Constraints on the Blur Model
Tae-Shick Wang, Kang-Sun Choi, Jong‐Woo Han, Sung-Hyun Cheon, Sung-Jea Ko · ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications · 2009
In this paper, a robust blind blur identification method is proposed which can estimate a reliable isotropic point spread function (PSF). We first identify regions where ideal edge components are expected, and estimate candidate PSFs from the regions. Then, the most reliable PSF is chosen from the candidates by applying the proposed verification process based on the deterministic constraints on the blur model. Experimental results show that the proposed method can estimate the PSF almost identical to the original PSF in various test images.