Design and implementation of an FPGA-based realtime face recognition system using spatial correlation function

This paper presents a simple and efficient design of a face recognition system, where feature extraction algorithm is employed based on the principle of spatial cross-correlation. In the feature extraction process, instead of processing the entire image at a time, only a pair of rows or columns of an image is considered which makes the algorithm very efficient and low-cost. Considering the cross-correlations between the pairs, a unique 1-D signature of a 2-D face image is obtained which represents the variation in the face geometry along the vertical or horizontal direction. It is shown that the resulting vertical and horizontal features provide high compactness within the class and separation between the classes. It is found that the proposed design can provide a satisfactory recognition performance for different standard databases. The results of hardware implementation in terms of resources used and processing speed have also been presented.