Abstract
In this paper, we propose a simple effective high-contrast intensity prior for text image deblurring based on the distinct properties within sharp text images and blurred text images. We develop an iterative and efficient optimization method to solve the objective function based on the high-contrast intensity prior for the blur kernel. We split the objective function into two sub-problems. We simplify one sub-problem to make its computation more efficient. We rewrite the other sub-problem based on the intensity space by changing it to the gradient space to make its solution stable. The proposed method can be applied to text images and even real-world images with very good results compared to some state-of-the art methods.