Abstrakt

Computer Vision Approach for Retrieving Unconstrained Blurred Images

K.Sridevi

Face Recognition has been of great importance in different fields of technology. But when blurring come to picture face recognition becomes difficult. There has many approaches proposed in this context like blind image deconvolution, image statistics etc. But all these approaches concentrate mainly on the blurring part alone. The problem of unconstrained face recognition from remotely acquired images. The main factors that make this problem challenging are image degradation due to blur and appearance variations due to illumination and pose. Here in this approach the illumination defects are together considered with the blur problems. Based on this set theoretic characterization proposed a blur-robust algorithm whose main step involves solving simple convex optimization problems. To overcome this problem, the proposed technique is based on computer vision. And the violo- jones method is the fast face detection in skin color detector. By using this method avoid the problem in existing system and get good performance. It concerned with the theory for building artificial systems that obtain information from images. Based on this characterization proposed a blur and illumination robust algorithm