الخلاصة

The task of face recognition has been actively researched in recent years because of its many applications in various domains. This study suggested new and novel method to matching the input face image with face images in database based on GSVD. Euclidian distance for the norm of two factors resulted from GSVD of each pair of images was determined. When the distance less or equal to specific threshold we decide the two images matched. The accuracy of this proposed algorithm was high comparing with other algorithms and it reached up to 97. 21%. The algorithm tested with images from ORL database and Indian face database.