C21. Single image motion deblurring using Genetic Algorithms

One of the key problems of restoring a degraded image from motion blur is the estimation of the unknown blur filter from a single input blurred image. Many blind deconvolution methods typically assume frequency-domain constraints on images, simplified parametric forms for the motion path during camera shake or use multiple input images. The paper proposes an algorithm for removing motion blur from a single input blurred image using Genetic Algorithms. Genetic Algorithms are applied in science and engineering as adaptive algorithms for optimizing practical problems. Also recent research in natural image statistics is exploited, which shows that photographs of natural scenes typically obey heavy-tailed distribution. Both linear and non-linear motion blur are handled. Experiments on a wide data set of standard images degraded with different kernels of different sizes demonstrate the efficiency of the proposed approach especially in small blur lengths.