Person identification from video by similarity between feature set

The recognition of the face from videos has numerous applications in Video Surveillances and Computer Vision. The main challenge of detecting face image in videos is the pose and the illumination variations and sudden changes in the movement of the object. The proposed system analyzes and recognizes the exact face image from the video even though there are pose variation and illumination variation while the existing systems deals with the recognition of the face images from still images. The image gradient value and the histogram values were calculated. These will be helpful for the identification of the face positions continuously in the video frame. The Hog features are extracted its used for identification of the particular person and Bhattacharya distance calculated. The results shows that the recognition rate of the proposed system is increased compared to other existing systems.