Improving iris recognition through new target vectors in MLP artificial neural networks

Authors:
José Ricardo Gonçalves Manzan;Shigueo Nomura;Keiji Yamanaka;Milena Bueno Pereira Carneiro;Antônio C. Paschoarelli Veiga
Affiliations:
Faculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, Brasil;Faculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, Brasil;Faculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, Brasil;Faculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, Brasil;Faculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, Brasil
Venue:
ANNPR'12 Proceedings of the 5th INNS IAPR TC 3 GIRPR conference on Artificial Neural Networks in Pattern Recognition
Year:
2012

Citing 6
Cited 0

Fundamentals of neural networks: architectures, algorithms, and applications

Fundamentals of neural networks: architectures, algorithms, and applications
Neural Network Analysis, Architectures and Applications

Neural Network Analysis, Architectures and Applications
An Iris Biometric System for Public and Personal Use

Computer
High Confidence Visual Recognition of Persons by a Test of Statistical Independence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Improving neural networks generalization with new constructive and pruning methods

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology - SBRN'02
Convergence analysis of convex incremental neural networks

Annals of Mathematics and Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper compares the performance of multilayer perceptron (MLP) networks trained with conventional bipolar target vectors (CBVs) and orthogonal bipolar new target vectors (OBVs) for biometric pattern recognition. The experimental analysis consisted of using biometric patterns from CASIA Iris Image Database developed by Chinese Academy of Sciences - Institute of Automation. The experiments were performed in order to obtain the best recognition rates, leading to the comparison of results from both conventional and new target vectors. The experimental results have shown that MLPs trained with OBVs can better recognize the patterns of iris images than MLPs trained with CBVs.