基于集成学习的虹膜分割算法  

Research on Iris Segmentation Algorithm Based on Ensemble Learning

作　　者：孙佳倩 朱金荣[1] 张小宝 张云恺 龚卫娟 SUN Jiaqian;ZHU Jinrong;ZHANG Xiaobao;ZHANG Yunkai;GONG Weijuan(School of Physical Science and Technology,Yangzhou University,Yangzhou 225100,China)

机构地区：[1]扬州大学物理科学与技术学院,江苏扬州225100

出　　处：《电子科技》2025年第3期88-94,共7页Electronic Science and Technology

基　　金：国家自然科学基金(61802336)。

摘　　要：针对虹膜图像在分割过程中细节分割不准确、边界分割不圆滑以及易受噪声影响等问题,文中提出了一种基于集成学习的虹膜分割算法。相较于传统集成学习算法,文中算法基于皮尔森系数法选择合适的模型作为基学习器,从而提高了集成学习的性能。选用U^(2)-Net、DeepLabv3+以及PSPNet作为同质个体学习器在CASIA-Iris-Interval数据集上进行训练,并预测得到对应的虹膜分割预测结果。对预测结果进行CLAHE和Gamma校正等图像增强操作得到新的预测结果图,选取加权平均法作为集成算法将基学习器的预测结果进行集成学习,从而得到最终的虹膜分割预测结果。测试结果表明,在3个不同的评估指标下,相较于基学习器,所提算法的准确率提升了1%,平均交并比提升了3.8%,宏平均分数提升了2.4%,视觉效果和客观评价指标均有所提升。In view of the problems such as inaccurate detail segmentation,unsmooth boundary segmentation and easy to be affected by noise,an iris segmentation algorithm based on ensemble learning is proposed in this study.Compared with the traditional ensemble learning algorithm,the appropriate model is selected as the base learner based on Pearson coefficient method,so as to improve the performance of ensemble learning.U^(2)-Net,DeepLabv3+and PSPNet are selected as homogeneous individual learners to train on the CASIA-Iris-Interval dataset,and the corresponding iris segmentation prediction results are obtained.CLAHE and Gamma correction and other image enhancement operations are performed to obtain a new prediction result graph.Weighted average method is selected as an integrated algorithm to integrate the prediction results of the basis learner,so as to obtain the final prediction results of iris segmentation.The test results show that the accuracy of the proposed algorithm is improved by 1%,the average crossover ratio is improved by 3.8%,the average macro score is improved by 2.4%,and the visual effect and objective evaluation index have better segmentation effect when compared with the base learner under three different evaluation indexes.

关 键 词：虹膜分割 集成学习 学习器 U^(2)-Net DeepLabv3+ PSPNet 皮尔森系数法 图像处理 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]