New performance metrics for blind image restoration

Abstract

Terminating an iterative blind image restoration process pauses a formidable challenge to a human observer. Since many iterative processes may takes few hundreds to thousands to converge to a final result (if it converges at all), an automated process closely mimicking the human visual system (HVS) will certainly benefit the image restoration process as well as add to the consistency of the final decision. We have modified some image fidelity metrics such as MSE, Correlation Value and Laplacian Correlation Value metrics to be used in iterative blind restoration of blurred images. A detailed discussion and some experimental results pertaining to these issues are presented in this article.