Attention guided U-Net for accurate iris segmentation
Attention guided U-Net for accurate iris segmentation
复制标题
注意力引导 U-Net 用于精确虹膜分割
DOI：
10.1016/j.jvcir.2018.10.001
复制
发表时间：
2018-10-01
影响因子：
2.6
通讯作者：
Li, Shaozi
中科院分区：
文献类型：
--
作者：
Lian, Sheng;Luo, Zhiming;Li, Shaozi
虹膜分割是提高虹膜识别准确性以及医疗问题的关键一步。现有方法通常使用全眼图像作为网络学习的输入，没有考虑虹膜仅出现在眼睛特定区域的几何约束。因此，此类方法很容易受到虹膜区域外不相关噪声像素的影响。为了解决这个问题，我们提出了注意力U-Net（Arf-UNet），它指导模型学习更多的区分特征来分离虹膜和非虹膜像素。 ATT-UNet 首先回归潜在虹膜区域的边界框并生成注意掩模。然后，将掩模用作加权函数，与模型中的判别性特征图合并，使分割模型更加关注虹膜区域。我们在 UBIRIS.v2 和 CASIA.IrisV4-distance 上实施我们的方法，平均错误率分别为 0.76% 和 0.38%。实验结果表明，我们的方法在具有挑战性的场景的可见波长和近红外虹膜图像上实现了一致的改进，并超越了其他代表性的虹膜分割方法。 (C) 2018 Elsevier Inc. 保留所有权利。
Iris segmentation is a critical step for improving the accuracy of iris recognition, as well as for medical concerns. Existing methods generally use whole eye images as input for network learning, which do not consider the geometric constrain that iris only occur in a specific area in the eye. As a result, such methods can be easily affected by irrelevant noisy pixels outside iris region. In order to address this problem, we propose the ATTention U-Net (Arf-UNet) which guides the model to learn more discriminative features for separating the iris and non-iris pixels. The ATT-UNet firstly regress a bounding box of the potential iris region and generated an attention mask. Then, the mask is used as a weighted function to merge with discriminative feature maps in the model, making segmentation model pay more attention to iris region. We implement our approach on UBIRIS.v2 and CASIA.IrisV4-distance, and achieve mean error rates of 0.76% and 0.38%, respectively. Experimental results show that our method achieves consistent improvement in both visible wavelength and near-infrared iris images with challenging scenery, and surpass other representative iris segmentation approaches. (C) 2018 Elsevier Inc. All rights reserved.