Volume 18, No. 6, 2021
Comparative Study On Iris Recognition Using Deep Learning
D. MEENAKSHI , Dr. M. SIVAJOTHI , Dr. M. MOHAMED SATHIK
Abstract
Iris Recognition has been one of the most robust means of biometric recognition. In recent years, there are so many researches in iris recognition using deep learning. In this paper, three recent researches on iris recognition are compared and analyzed for the in-depth study on iris recognition. All the three researches use deep learning for its method which are VGGNet, Residual Convolutional Neural Network (Residual CNN) and Dense Fully Convolutional Neural Network (DFCN). Experiments results are compared on CASIA 1000 and IITD databases for all the three models. The DFCN architecture achieves good accuracy when compared to other methods.
Pages: 8724-8734
Keywords: Deep Learning, Convolution Neural Network, Biometric Recognition.