Multilayer Perceptron Neural Network In Classifying Gender Using Fingerprint Global Level Features

Siti Fairuz, Abdullah and Ahmad Fadzli Nizam, Abdul Rahman and Zuraida, Abal Abas and Wira Hidayat, Mohd Saad (2016) Multilayer Perceptron Neural Network In Classifying Gender Using Fingerprint Global Level Features. Indian Journal Of Science And Technology (INDJST), 9 (9). pp. 1-6. ISSN 0974-6846

Text Multilayer Perceptron Neural Network In Classifying Gender Using Fingerprint Global Level Features.pdf - Published Version Download (356kB)

Abstract

Background/Objective: A new algorithms of gender classification from fingerprint is proposed based on Acree 25mm2 square area. The classification is achieved by extracting the global features from fingerprint images which is Ridge Density, Ridge Thickness to Valley Thickness Ratio (RTVTR) and White Lines Count. The objective of this study to test the effectiveness of the this new algorithm by looking the classification rate. Multilayer Perceptron Neural Network (MLPNN) used as a classifier. Methods: This new algorithm is tested with a database of 3000 fingerprint in which 1430 were male fingerprint and 1570 were female fingerprints. Classification part is tested with different test option. Findings: This study found that women tends to have higher Ridge Density, higher white lines count and higher ridge thickness to valley thickness ratio compared to male same as the previous study. Therefore, we can conclude that this new algorithm is very efficient and effective in classifying gender. Conclusion: The overall classification rate is 97.25% has been achieved.

Item Type:	Article
Uncontrolled Keywords:	Fingerprint, Gender Classification, Global Features, Multilayer Perceptron Neural Network
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Information and Communication Technology
Depositing User:	Mohd Hannif Jamaludin
Date Deposited:	27 Sep 2016 00:43
Last Modified:	12 Sep 2021 03:51
URI:	http://eprints.utem.edu.my/id/eprint/17251
Statistic Details:	View Download Statistic

Actions (login required)

View Item