Iris recognition using self-organizing neural network
Student Conference on Research and Development - Trang 169-172
Tóm tắt
Among biometric systems for user verification, iris recognition systems represent a relatively new technology. Our system consists of two main parts: a localizing iris and iris pattern recognition. The raw image is captured using a digital camera. The iris is then extracted from the background after enhancement and noise elimination. Due to noise and the high degree of freedom in the iris pattern, only parts of the iris structure are selected for recognition. The selected iris structure is then reconstructed into a rectangle format. Using a trained self-organizing map neural network, iris patterns are recognized. The overall accuracy of our network is found to be about 83%.
Từ khóa
#Iris recognition #Neural networks #Information technology #Biometrics #Eyelids #Pattern recognition #Digital cameras #Image reconstruction #Shape #Fingerprint recognitionTài liệu tham khảo
james, 1992, Neural Networks Algorithms Application and Programming Techniques
patterson, 1995, Artificial Neural Network
wilds, 1994, A System For Automated Iris Recognition, 121
bose, 1996, Neural Network Fundamentals with Graphs Algorithms and Applications
10.1109/78.668573
hagan, 1996, Neural Network Design
2000, Basic of Iris Recognition, Iridian Technology
jain, 1999, Industrial Applications of Neural Networks
haykin, 1999, Neural Networks A Comprehensive Foundation
foster, 1994, Designing and Building Parallel Programs
daugan, 1992, High Confidence Personal Identification By Repaid Video Analysis Of Iris Texture, Proceedings International Carnahan Conference on Security Technology, 50
10.1109/34.244676