Multimodal Biometric System: A Feature Level Fusion Approach
K. Geetha, V. M. Radhakrishnan · International Journal of Computer Applications · 2013
Biometric systems are automatic process to identify a person through physical traits or to verify his/her identity.Various systems were implemented and used over years, and they include systems based on fingerprints, irises, facial images, hand geometry, and speaker recognition.For successful implementation of biometric systems,it is required to address many issues like accuracy, efficiency, robustness, applicability, and universality.Single modality based recognition verification s not very robust while combining information from various biometric modalities provides better performance.The multimodal biometric system uses multiple biometrics and integrates information for identification.It compensatesthe limitations of unimodal biometric systems.In this paper, a Multimodal biometric system proposed based on fingerprint and palmprint.Coiflet wavelets are used to extract features from the fingerprint and palmprint.It is proposed to fuse the extracted features and these features are classified using Support Vector Machine (SVM).