A hybrid feature extraction technique for face recognition

The accuracy of any face recognition is important for many military and civilian real time applications. Based on current literature it has been proven that, the accuracy of a face recognition system can be extremely improved using a hybrid feature extraction technique. This paper presents a hybrid feature extraction technique to obtain high level of recognition accuracy. The facial topographical features are extracted using manual segmentation of facial regions of eyes, nose and mouth. The Gabor transform of the maximum of these regions are then extracted to calculate the local representations of these regions. In the classification stage, the Nearest Neighbour method (KNN) is exploited to calculate the distances between the three regions feature vectors and the corresponding stored vectors. The system results in excellent recognition accuracy using faces94, FEI and ORL databases. It is observed that, high recognition accuracy rate can be obtained when the facial images are taken carefully with front pose and with only slight expression changes. The future work will be on implementing this system in a FPGA device for a real time application such as a door access control system.