.png){kind=icon}
.png){kind=icon}
Return
Iris recognition using artificial neural networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2010.11.029.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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. Brain-Maker 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. (C) 2010 Elsevier Ltd. All rights reserved.
Keywords:
Iris recognition
Feedforward neural networks
Backpropagation training algorithm
Image data partitioning techniques
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W