Deblurring filter design based on fuzzy regression modeling and perceptual image quality assessment

Images captured by digital cameras are generally not perfect as image blurring is usually generated by camera motion through long hand-held exposure. Deblurring filters can be used to improve image quality by removing image blur. Prior to develop a deblurring filter, a simulator for image quality assessment is essential to optimize filter parameters. Although subjective image quality assessment (subjective IQA) is commonly used for evaluating the visual effect of digital images for a wide range of image processing applications, it is inconvenient to be implemented in real-Time. Generally, statistical regression is used to generate a functional map to correlate the subjective IQA and the objective image quality metrics. However, it cannot address the uncertainty caused by human judgment during the subjective IQA. This paper first proposes a fuzzy regression method to develop the functional map that overcomes the limitation of statistical regression that cannot account for uncertainty introduced through human judgment. Based on the fuzzy regression models, the deblurring filter parameters can be optimized. Experimental results show that the satisfactory deblurring can be achieved on blurred images captured by a smartphone camera.