Spatial-Frequency Features Extracting for Facial Image Retrieval from a Big Image Database

In this paper, a new method is presented to feature extraction from facial images. The main purpose of this paper is probe image retrieval from a big database. By increasing the size of the database, the similarities between people increases and the separation capability decreases. The proposed method increases the distance between peoples in feature space by extracting appropriate features. This method is based on properties of the human vision system and sequentially extracts features in top-down manner. For this purpose, spatial- frequency features are used. In this method, by applying concentric windows in different size on the facial image, the content of each window are mapped to frequency space. The change of frequency components in different windows forms the feature space of image. Then frequency component with high separation capability between face images is remained by appropriate filter. In the end, the final image is retrieved from database by Euclidean distance criterion. In this paper the FERET database is used. Recognition rate compared with the best current method in similar size of database, with 2% improvement reached to 99%. By increasing database size to 990 classes, 90.4% of recognition rate is achieved.