No abstract

Biometrics is the art of distinguishing or analysing the identity of a person in view of physiological or behavioural attributes. Biometric recognizable strategies have turned out to be more productive, natural and simple for human identification compared to conventional techniques. Biometric validation frameworks basically design recognition frameworks, the physiological qualities like finger impression, face, and hand geometry, DNA and iris acknowledgment. The primary aim of the method is to build up a biometric validation framework by utilizing the ear and fingerprint images to distinguish a genuine user. In pre-processing step, all images are enhanced by thinning and binarization method for extracting the features. Then, a feature extraction system incorporates Minutiae and Singular point procedure for fingerprint images. Ear features are extracted by utilizing Speed Up Robust Features (SURF) and Binary Robust Invariant Scalable Keypoints (BRISK) systems. The features are fused by concatenating the fingerprint and ear features to obtain accurate information. Finally, matching is completed by registration and similarity score process and after that by utilizing the threshold esteems, the users are distinguished as genuine or an imposter. The experimental results demonstrated that the proposed multi-model biometric accomplished 95.66% precision with the error rate of 0.0434.