Title
Biometrical Authentication of Twins from Side-View using Hybrid Approach
Author(s)
Dr. R. P. Dubey (Vice-Chancellor)
Document Abstract
In the recent times frontal face images have been used for the biometrical authentication of twins. The present paper incorporates the frontal face images of twins only for the formation of corpus. But for the biometrical authentication, side-view of the twins face images has been analysed using hybrid approach, which means the combination of Artificial Neural Network (ANN) and Genetic Algorithm (GA). The work has been carried out in two phases. In the first phase, formation of the FACE_MODEL as a corpus using frontal face images of one subjects from twins have been done. In the second phase, the model or the corpus has been used at the back-end for Biometrical Authentication using a proposed algorithm called HABAT (Hybrid Approach Biometrical Authentication for Twins). The authentication process has been carried out with the help of an unknown zero-degree (parallel to the surface plain) oriented image of same subject from twins which is in the corpus and second subject from that same twins. Hence relevant features with switching orientation in image from Zero-degree (parallel to the surface plain) to higher degree with 10-degree change have been matched with the corpus. The classification process of acceptance and rejection has been done after best-fit matching. The proposed algorithm has been tested with 10 subjects of varying age groups. The result has been found very satisfactory with the data sets and may be helpful in bridging the gap between computer and authorized subject for more system security.
Publisher Name
Bharat Journal of Science Technlogy and Humanities