Human ear identification system using shape and structural features based on SIFT and ANN classifier

Abstract

People have become more interested in biometrics recognition as technology has advanced. Biometrics is the study of automatic systems for distinguishing people related to physical or behavioural features. Methods for finding favourable biometric traits have acquired more attention in recent years. The ear is among the most consistent biometric traits because it does not alter with aging or emotion. The human ear is an excellent source of data for passive personal authentication. The ear looks to be an excellent potential solution because it is accessible, images are easily obtained, and the ear structure doesn't change over the years. The ear meets a biometric criterion (universality, distinctiveness, durability, and collectability). The biometric field is working hard to develop automated individual identification using ear images. Several face recognition approaches fail in this present COVID-19 outbreak due to the mask-wearing situation. The human ear is attractive data for passive personal authentication because it does not need the individual's involvement to recognize the ear. In this research, we suggested an automatic ear identification system using Scale Invariant Feature Transform (SIFT) and an Artificial Neural Network (ANN).