A Simple and Accurate CNN for Iris Recognition
A Simple and Accurate CNN for Iris Recognition
复制标题
DOI：
10.23919/apsipaasc55919.2022.9980056
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Shokei Kawakami;Hiroya Kawai;Koichi Ito;T. Aoki;Yoshiko Yasumura;Masakazu Fujio;Yosuke Kaga;Kenta Takahashi
中科院分区：
文献类型：
--
作者：
Shokei Kawakami;Hiroya Kawai;Koichi Ito;T. Aoki;Yoshiko Yasumura;Masakazu Fujio;Yosuke Kaga;Kenta Takahashi
基于深度学习的虹膜识别是虹膜识别领域的一种新方法，目前已经提出了许多方法。与日益复杂的基于卷积神经网络的虹膜识别方法相比，本文提出了一种简单、准确的卷积神经网络作为虹膜识别的基线。本文提出了一种对归一化虹膜图像进行匹配的方法，该方法将虹膜分成四个区域，并利用细胞神经网络对每个区域进行特征提取。为了减少眼皮、睫毛等非虹膜区域的影响，通过选择训练区域、计算基于虹膜区域的加权匹配分数、引入适合虹膜图像的数据增强以及引入注意力机制来提高识别准确率。通过在公共虹膜图像库上的一组实验，我们证明了该方法比OSIRIS和其他CNN具有更高的识别准确率。
Iris recognition using deep learning is a new approach in iris recognition, and many methods have been proposed so far. We consider a simple and accurate Convolutional Neural Network (CNN) as a baseline for iris recognition in contrast to the increasingly complex CNN-based iris recognition methods. In this paper, we propose a method for matching normalized iris images by dividing the iris into four regions and extracting features from each region using CNN. To reduce the influence of non-iris regions such as eyelids and eyelashes, we improve the recognition accuracy by selecting regions for training, calculating weighted matching scores based on iris regions, introducing data augmentation suitable for iris images, and introducing an attention mechanism. Through a set of experiments using the public iris image database, we demonstrate that the proposed method exhibits higher recognition accuracy than OSIRIS and other CNNs.