Non-linear motion deblurring in single images using genetic algorithms | ||||
The International Conference on Electrical Engineering | ||||
Article 46, Volume 8, 8th International Conference on Electrical Engineering ICEENG 2012, May 2012, Page 1-13 PDF (874.51 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2012.30792 | ||||
View on SCiNiTO | ||||
Authors | ||||
Salsabil El-Regaily; H. El-Messiry; M. Abd El-Aziz; M. I. Roushdy | ||||
Faculty of Computer and Information Sciences, Ain Shams University, Cairo, Egypt. | ||||
Abstract | ||||
One of the key problems of restoring a degraded image from motion blur is the estimation of the unknown non-linear 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 with specific characteristics. This paper proposes an algorithm for removing non-linear motion blur from a single input blurred image using Genetic Algorithms (GAs), by finding the proper parameters and goal function. Also recent research in natural image statistics is exploited, which shows that photographs of natural scenes typically obey heavy-tailed distribution. The Point Spread Function entries are used as the parameters of the GA. 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 compared to other algorithms with reasonable running times for a GA. | ||||
Keywords | ||||
Camera Shake; Blind Image Deconvolution; Genetic Algorithm; Non-Linear Motion Blur | ||||
Statistics Article View: 131 PDF Download: 211 |
||||