Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
High Confidence Visual Recognition of Persons by a Test of Statistical Independence
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Expert: Intelligent Systems and Their Applications
Spiking neural network and wavelets for hiding iris data in digital images
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special Issue on Bio-Inspired Information Hiding; Guest editors: Jeng-Shyang Pan, Ajith Abraham
High performance iris recognition based on 1-D circular feature extraction and PSO-PNN classifier
Expert Systems with Applications: An International Journal
A human identification technique using images of the iris andwavelet transform
IEEE Transactions on Signal Processing
An introduction to biometric recognition
IEEE Transactions on Circuits and Systems for Video Technology
Compact yet efficient hardware implementation of artificial neural networks with customized topology
Expert Systems with Applications: An International Journal
Iris localization in frontal eye images for less constrained iris recognition systems
Digital Signal Processing
Iris recognition using combined support vector machine and Hamming distance approach
Expert Systems with Applications: An International Journal
Hi-index | 12.05 |
Biometrics recognition is one of the leading identity recognition means in the world today. Iris recognition is very effective for person identification due to the iris' unique features and the protection of the iris from the environment and aging. This paper presents a simple methodology for pre-processing iris images and the design and training of a feedforward artificial neural network for iris recognition. Three different iris image data partitioning techniques and two data codings are proposed and explored. BrainMaker simulations reveal that recognition accuracies as high as 93.33% can be reached despite our testing of similar irises of the same color. We also experiment with various number of hidden layers, number of neurons in each hidden layer, input format (binary vs. analog), percent of data used for training vs testing, and with the addition of noise. Our recognition system achieves high accuracy despite using simple data pre-processing and a simple neural network.