Automatic authentication systems, using biometric technology, are becoming increasingly important with the increased need\r\nfor person verification in our daily life. A few years back, fingerprint verification was done only in criminal investigations.\r\nNow fingerprints and face images are widely used in bank tellers, airports, and building entrances. Face images are easy to\r\nobtain, but successful recognition depends on proper orientation and illumination of the image, compared to the one taken at\r\nregistration time. Facial features heavily change with illumination and orientation angle, leading to increased false rejection as\r\nwell as false acceptance. Registering face images for all possible angles and illumination is impossible. In this work, we proposed a\r\nmemory efficient way to register (store) multiple angle and changing illumination face image data, and a computationally efficient\r\nauthentication technique, using multilayer perceptron (MLP). Though MLP is trained using a few registered images with different\r\norientation, due to generalization property of MLP, interpolation of features for intermediate orientation angles was possible. The\r\nalgorithm is further extended to include illumination robust authentication system. Results of extensive experiments verify the\r\neffectiveness of the proposed algorithm.
Loading....