Multimodal Biometric Recognition Using Sift and K-Means Algorithm

Abstract: Most biometric systems that are presently used in real time applications typically use a single biometric characteristic to authenticate the user. A biometric system which is based only on a single biometric identifier in making a personal identification is often not able to meet the desired performance requirements. Multimodal b io metrics is an emerging field of bio metric technology, where more than one biometric trait to improve the combined performance. We design a bimodal bio met ric system wh ich integrates FKP and Face. Hence this paper has focused on the extraction o f featu res fro m FKP and Face using Scale Invariant Feature Transform ( SIFT), and the key po ints are derived fro m FKP and Face and then they are clustered using K-Means Algorithm. The centroid, mean and variance of key extracted image of K-Means are stored in the database which is compared with the query FKP and Face features to prove the recognition and authentication . The co mparison is based on the XOR operat ion . Results are performed on the Poly-U FKP and Face database to check the proposed FKP and Face recognition method. It can be used to overcome some of the limitations of a single b io metrics, increases the performance.

Keywords: Bio metric, SIFT A lgorith m, Feature Extract ion, K-Means Algorith m