Abstract—Abstract—Face recognition is one of the most important applications of computer vision in recent years. The developed multimodal biometric system possesses a number of unique qualities, starting from utilizing principal component analysis and Fisher’s linear Discriminant methods for individual matcher’s identity authentication and utilizes the novel feature fusion method to consolidate the results obtained from different biometric matchers. In this paper, we present a bimodal face-finger recognition system that fuses results from both Principal Component Analysis and Fisher face projections. The proposed approach is tested on a real database consisting of 500 images and shows promising results compared to other techniques. The main goal of Bi Modal Identification system is to develop the security system for the areas that require high level of security. The Receiver Operating Characteristics also shows that the proposed method is superior compared to other techniques under study.
Index Terms—Fisher faces, principal component analysis, receiver operating characteristics curve.
C. N. Dinakardas is with Department of ECE of Lourdes Matha College of Science & Technology, Trivandrum, India. (e-mail: dinakardas@gmail.com). S. Perumal Sankar is with the Department of ECE, CAPE Institute of Technology, Kanyakumari, India (e-mail: spsankar2004@yahoo.co.in). Nisha George, is with the Electronics & Communication Engineering Department, Lourdes Matha College of Science & Technology, Trivandrum, India (e-mail: ddcnisha@gmail.com).
Cite:C. N. Dinakardas, S. Perumal Sankar, and Nisha George, "Bi Modal Person Identification System," International Journal of Machine Learning and Computing vol.3, no. 2, pp. 186-199, 2013.