AN ENHANCED MULTI-MODAL BIOMETRIC AUTHENTICATION

Author Reg. ID: TIJER_100057

Published Paper Id: TIJER2206030

Published In: Volume 9 Issue 6, June-2022

Abstract: A multi-modal biometrics (MMB) system incorporates information as of more than one biometric modality for enhancing each biometric system’s performance. The recognition system encompasses robustness, accuracy, along with recognition rate issues. The model deals with biometric authentication and its implementation in a 3- tier multimodal architecture which works on the basic principle of identification and authentication. As the applications of computers are increasing in every sector, the requirement of a dependable authentication plan to affirm the character of an individual is immense. The proposed MMB system is on FLSL fusion method and Modified Deep Learning Neural Network (MDLNN) to enhance the performance. The face, ear, retina, fingerprint, and front hand image traits are considered. This comprises image enhancement, segmentation, feature extraction, feature reduction, rule generation, and identification phases. The Viola-Jones Algorithm (VJA) segments the facial parts, and the Penalty and Pearson Correlation-based Watershed Segmentation (PPWS) algorithm eliminates the unwanted information in the ear, finger traits and also the blood vessel of the retina image. The features are extracted as of images, and are inputted to the MDLNN to classify the person as genuine or imposter.

Keywords: AN ENHANCED MULTI-MODAL BIOMETRIC AUTHENTICATION

Downloads: 000580

Page No: 151-158

Country: -, -, -

Research Area: Science and Technology

Published Paper URL: https://tijer.org/TIJER/viewpaperforall?paper=TIJER2206030

Published Paper PDF: https://tijer.org/TIJER/papers/TIJER2206030

Click Here to Download This Article

Article Preview