A Novel Approach for Blurred and Noisy Face Image Recognition

This paper presents the blurred and noisy face image recognition. The main factors that make this problem challenging are image degradation due to blur and noise. Motion blur is simply an undesired effect. Restoration of blur image is very important in many of the cases like identification of criminal face in blurred image. The motion blur can be occurred due by the movement of the object or the camera. The photos captured in cameras make the camera as stationary and the object is in the movement or vice versa, so there is a higher probability of inducing of the motion blur and a noise on the image. In the identification of a person on the event of a crime so, we present the novel approach for the recognition of a person by the estimation of the blur. The features are extracted using the principle component analysis, later face recognition is carried out by matching the obtained features with the database features. The experimental results show the better recognition of a person in the FEI database.