An Improved Self-Updating Face Recognition Authentication System
Anitha Devi, A. Kavitha, Anushree Marimuthu · International Review on Computers and Software (IRECOS) · 2013
Face recognition authentication system has become an active research area in the field of biometrics and security. A number of research works have been developed and is available in the literature. Although the available approaches provide good results under particular conditions, the illumination alterations, occlusions and recognition time are still main issues in face recognition authentication systems (FRAS). The main reason for the overall performance degradation is due to the transformations in appearance of the user based on the aspects like ageing, beard growth, sun-tan etc. In order to overcome the above drawback, Self-update process has been developed in which, the system learns the biometric attributes of the user every time the user interacts with the system and the information gets updated automatically. A more common issue in biometric systems is the corruption of biometric traits due to misclassification. This research utilizes an efficient FRAS, based on three classification algorithms. The proposed method consists of various processes like Face segmentation, Face Normalization and Classification. Efficient techniques have been used in each phase of the FRAS to get improved results.