[This article belongs to Volume - 54, Issue - 02]
Gongcheng Kexue Yu Jishu/Advanced Engineering Science
Journal ID : AES-09-12-2022-541

Title : INDIVIDUATE IDENTICAL TWINS BY FACIAL FEATURES AND EXTERNAL EAR PATTERN USING NEURAL NETWORKS
K.K. Rehkha1, Dr.Viji Vinod2

Abstract :

Biometrics is a mechanization which is an emerging breakthrough in case of security to identify a person’s unique personality. It is utilized to determine a person’s uniqueness by means of his/her materialistic attribute such as finger print, retina, facial features, iris, dental traits etc. Other features which can be considered as biometric are external pattern of the ear, hand veins, gait, keypad touch, voice recognition etc. Additionally, biometrics is also considered as a major authentication in enterprise security system. This scientific knowledge is predominantly used for surveillance purposes. There is discrete category of biometrics such as Biological Biometrics, Morphological Biometrics and Behavioral Biometrics. Biometrics is considered to give us immense accuracy rate, however the task is extremely crucial taking identical twins into consideration. The Research Literature is on identification of Monozygotic twins by considering their biometrics of facial features and external ear pattern by using the hybrid model of RNN (Recurrent Neural Network) classification, CNN (Convolutional Neural Network), PSO (Particle Swarm Optimization) and MSVM (Multiclass Support Vector Machine).The features of the face i.e., nose, mouth and eyes are studied for analyzing the two identical twin images. This paper pulls together the literature review in the distinct field, implements with the assembled datasets and intimates’ feasibility for the forthcoming research study.