[This article belongs to Volume - 54, Issue - 02]
Gongcheng Kexue Yu Jishu/Advanced Engineering Science
Journal ID : AES-20-11-2022-459

Title : TEXTURE FEATURES AND KNN CLASSIFIER FOR PERSON IDENTIFICATION USING MULTIMODAL BIOMETRICS
Mahesh D M, Bhavya D N, Sharath Kumar Y H

Abstract :

: In this work, we proposed a method for person identification using Texture features. We used fingerprint and ear features traits and fused. The proposed feature extraction technique like LBP, LTP, LQP and ELLBP was used to extract the features from ear and fingerprint images. These extracted features were stored in the database. We fuse the texture features using concatenation rule and select discriminative texture features by employing wrapper feature selection methods. For testing, the features were extracted and compared with the features stored in the database and matching was performed using KNN Classifiers with different distance measure. Performance of the system was analyzed with individual traits, fused fingerprint and ear features, and other feature extraction methods LBP, LTP, EEIPD and ELLBP. So as to improve accuracy rate and to provide a more reliable and secured multimodal system for person identification.