For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Iris Segmentation Based on Improved U-Net Network Model
Chunhui GAO Guorui FENG Yanli REN Lizhuang LIU
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2019/08/01
Online ISSN: 1745-1337
Type of Manuscript: LETTER
Category: Neural Networks and Bioengineering
iris segmentation, U-net, dense connection blocks, merge, skip connections, dilated convolution,
Full Text: PDF(1.1MB)>>
Accurate segmentation of the region in the iris picture has a crucial influence on the reliability of the recognition system. In this letter, we present an end to end deep neural network based on U-Net. It uses dense connection blocks to replace the original convolutional layer, which can effectively improve the reuse rate of the feature layer. The proposed method takes U-net's skip connections to combine the same-scale feature maps from the upsampling phase and the downsampling phase in the upsampling process (merge layer). In the last layer of downsampling, it uses dilated convolution. The dilated convolution balances the iris region localization accuracy and the iris edge pixel prediction accuracy, further improving network performance. The experiments running on the Casia v4 Interval and IITD datasets, show that the proposed method improves segmentation performance.