Multimodal Biometric Identification using DWT, Harris Corner and Support Vector Machine Classifier

Abstract

Biometric recognition systems use certain human characteristics such as voice, facial features, fingerprint, iris or hand geometry to identify an individual or verify their identity. These systems have been developed individually for each of these biometric modalities until they achieve remarkable levels of performance. Multimodal biometric systems combine different modalities in a unique recognition system. The multimodal fusion allows to improve the results obtained by a single biometric characteristic and make the system more robust to noise and interference and more resistant to possible attacks. The fusion can be carried out at the level of the signals acquired by the different sensors, of the parameters obtained for each modality, of the scores provided by unimodal experts or of the decision taken by said experts. In the fusion at the level of parameters or scores it is necessary to homogenize the characteristics coming from the different biometric modalities prior to the fusion process. This paper presents development of a multimodal biometric identification system based on two biometrics namely, the fingerprint and finger knuckle. Feature extraction is done using Harris Corner and DWT method and classification is accomplished using Support Vector Machine (SVM) classifier.