Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal La Multiapp
Muna Abdul Hussain Radhi
Computer Science Department, Collage of Science, Mustansiriyah University, Baghdad,Iraq
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Human Identification Model Considering Biometrics Features Muna Abdul Hussain Radhi
Journal La Multiapp Vol. 3 No. 4 (2022): Journal La Multiapp
Publisher : Newinera Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37899/journallamultiapp.v3i4.692

Abstract

In the medical field, brain classification is an effective technique for identifying a person through his brain print based on the hidden biometrics of high specificity included in the magnetic resonance images(MRI) of the brain, as this privacy strongly contributes to the issue of verification and identification of the person. In this paper, the brain print is extracted from the MRI obtained from 50 healthy people, which were passed through several pre-processing techniques in order to be used in the classification stage through convolutional neural network model, among those pre-classification stages, data collection after extracting the influential features for each image, which was based on linear discrimination analysis (LDA). The experimental results showed the importance of using LDA for feature extraction and adoption as input for K-NN and CNN classifiers. The classifiers proved successful in the classification if the features extracted with the help of LDA were adopted. Where CNN had the ability to classify with an accuracy of 99%, 82% for K-NN. The final stage in identifying a person through a brain fingerprint relied mainly on the model's success in classifying and predicting the remaining data in the testing stage.
Co-Authors