Multimodal Biometrics Feature Extraction using PCA and Bifurcation

Abstract

Biometric systems based on a single source of information suffer from limitations such as the lack of uniqueness and non-universality of the chosen biometric trait, noisy data and spoof attacks. Multimodal biometric systems fuse feature extracted from multiple biometric traits. An optimal combination of information can alleviate some of the limitations of unimodal biometric systems. Consequently, multimodal biometric systems achieve better performance compared to unimodal biometric systems and are being increasingly adopted in a number of applications. Major purpose of developing a multimodal biometric system is improving the level of security system using more than one biometric traits and optimal feature extraction and fusion techniques. The goal of this paper is to build multimodal biometric system using Ear and Fingerprint as biometric traits. Method, we are developing for extracting the features for ear is PCA (Principal component analysis) and method for finger print feature extraction is count minutiae and bifurcations. Fusion method used is Feature Level Fusion. Matching will decide accessibility of system. Here we are going to develop one of the most unique security systems which can be best path for developing more secure systems in Advanced Computing.