HUMAN IDENTIFICATION SYSTEM BASED ON BRAINPRINT USING MACHINE LEARNING ALGORITHMS

Abstract

In the medical field, due to the development of neuroimaging, several new methods of the biometric     field have been attending and favorable candidates for the identification of people. These methods are part of "covert biometrics" that involve the use of measures of clinical and medical images to identify them. The prime motivation to use an invisible (Hidden biometric) is the fact that attacks of a system can be very hard to deal with. This privacy strongly contributes to the increased strongest in the topic of person's verification and identification. In this article, he extracted a brain signature, called a "brain fingerprint" from brain (MRI) Magnetic Resonance Image, obtained from 30 healthy subjects as images (1739), these real data sets from Yarmok Medical Hospital. These brainprint in this work are considered to be a hallmark of the brain. The objective of this proposed work which is design a robust, accurate human identification using human brain print, the brain classification based on several phases, included Data acquisition, Feature extraction processing depend on linear discrimination analysis (LDA) to gain important and interesting features of every image calculated by (number of features in the class). The proposed system shows rise detection precision with the features extracted based on LDA with automatical classifier learning by K nearest neighbor (K-NN) and logistic regression (LR) from the LDA method gained with the LR algorithm of (93%) while LDA method gained (91%) with K-NN.