International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 65 - Number 3 |
Year of Publication: 2013 |
Authors: Basheer M. Nasef, Ibrahim E. Ziedan |
10.5120/10905-5832 |
Basheer M. Nasef, Ibrahim E. Ziedan . Enhancing Face Recognition using Average per Region. International Journal of Computer Applications. 65, 3 ( March 2013), 19-23. DOI=10.5120/10905-5832
Face recognition is concerned with the problem of correctly identifying face images and assigning them to persons in a database. This finds many practical applications in, e. g. , surveillance, identification systems and access control. In this paper, a face recognition method, with moderate computational requirements while preserving an acceptable recognition rate, is proposed based on the "average" features of gray images. The advantage of using average matching is that the structure of the face is strongly represented in its description along with its algorithmic and computational simplicity that makes it suitable for hardware implementation. The proposed technique is tested on the ORL face database benchmark and compared to well-established face recognition algorithms, namely Histogram, Hybrid Histogram & Eigen value (HHE). The results show the superiority of the new method over these methods in terms of recognition accuracy and computational time.