基于生成模型提升训练的深度学习虹膜识别方法  

Deep learning iris recognition method based on generative model boost training

作　　者：刘元宁[1,2] 朱琳 朱晓冬[1,2] 刘震[1,3] 吴浩萌[1] Yuan-ning LIU;Lin ZHU;Xiao-dong ZHU;Zhen LIU;Hao-meng WU(College of Computer Science and Technology,Jilin University,Changchun 130012,China;Key Laboratory of Symbolic Computation and Knowledge Engineering,Ministry of Education,Jilin University,Changchun 130012,China;Graduate School of Engineering,Nagasaki Institute of Applied Science,Nagasaki 851-0193,Japan)

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]吉林大学符号计算与知识工程教育部重点实验室,长春130012 [3]长崎综合科学大学研究生院工学研究科,长崎851-0193

出　　处：《吉林大学学报（工学版）》2022年第12期2924-2932,共9页Journal of Jilin University:Engineering and Technology Edition

基　　金：吉林省自然科学基金项目(YDZJ202101ZYTS144);国家自然科学基金项目(61471181).

摘　　要：提出了一种改进的深度虹膜分类模型EnhanceDeepIris,在生成网络的辅助下,对深度学习虹膜分类网络进行二次训练,使已经在原始训练集上收敛的分类网络继续训练,得到在测试集上泛化能力更好的网络。使用3个先进的图像分类网络VGG16、ResNet101和DenseNet121验证EnhanceDeepIris对深度学习分类网络的提升效果。在两个虹膜数据集CASIA-Iris-Thousand和JLU6.0上对该方法进行实验,结果表明,与传统数据增强方法相比,经过EnhanceDeepIris提升训练的分类模型识别精度更高、测试效果更稳定。An enhanced deep iris classification model EnhanceDeepIris was proposed,with the help of generating network,second trains a iris classification network of deep learning which has already converged on the original training set,to make it can continue be trained and get better generalization ability on the test set.Three most advanced image classification networks VGG16,ResNet101 and DenseNet121 were used to verify the improvement effect of EnhanceDeepIris on deep learning classification networks.The method was tested on two iris datasets CASIA-Iris-Thousand and JLU6.0.Compared with the traditional data augment method,the classification model trained by EnhanceDeepIris has higher correct recognition rate and more stable test effect.

关 键 词：计算机应用 深度学习 虹膜识别 图像生成 辅助分类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]