Iris Segmentation Using Feature Channel Optimization for Noisy Environments
- PDF / 1,382,253 Bytes
- 12 Pages / 595.224 x 790.955 pts Page_size
- 94 Downloads / 211 Views
Iris Segmentation Using Feature Channel Optimization for Noisy Environments Kangli Hao1 · Guorui Feng1 · Yanli Ren1 · Xinpeng Zhang1 Received: 8 November 2019 / Accepted: 14 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In recent years, iris recognition has been widely used in various fields. As the first step of iris recognition, segmentation accuracy is of great significance to the final recognition. However, iris images exhibit a variety of noise in the real world, which leads to lower segmentation accuracy than the ideal case. To address this problem, this paper proposes an iris segmentation method using feature channel optimization for noisy images. The method for non-ideal environments with noise is more suitable for practical applications. We add dense blocks and dilated convolutional layers to the encoder so that the information gradient flow obtained by different layers can be reused, and the receptive field can be expanded. In the decoder, based on Jensen-Shannon (JS) divergence, we first recalculate the weight of the feature channels obtained from each layer, which enhances the useful information and suppresses the interference information in the noisy environments to boost the segmentation accuracy. The proposed architecture is validated in the CASIA v4.0 interval (CASIA) and IIT Delhi v1.0 datasets (IITD). For CASIA, the mean error rate is 0.78%, and the F-measure value is 98.21%. For IITD, the mean error rate is 0.97%, and the F-measure value is 97.87%. Experimental results show that the proposed method outperforms other state-of-art methods under noisy environments, such as Gaussian blur, Gaussian noise, and salt and pepper noise. Keywords Iris segmentation · U-Net · Dense block · Dilated convolution · Feature channel optimization
Introduction The iris is considered to be the most robust biometric authentication information. Its stability is not affected by age, and the iris of each person has a distinctive pattern. Even among identical twins, the iris is quite different [1]. Compared with other biological features, the iris is easier to collect, and thus it plays an important role in the biometric authentication systems. Recently, open-source and commercial iris recognition software has emerged. Some advanced smartphones have been equipped with functions such as iris unlocking and iris payment authentication. To encourage more widespread use of iris recognition, researchers should strive to improve the accuracy of recognition in various noisy environments and reduce the time spent on this process. Guorui Feng
[email protected] 1
Shanghai Institute for Advanced Communication and Data Science and School of Communication and Information Engineering, Shanghai University, Shanghai, China
In the iris recognition system, there are three main parts: iris region segmentation, iris feature extraction, and matching recognition [2]. As the first step in the process, the segmentation accuracy directly affects the recognition reliability. The subsequent feature
Data Loading...
