摘要
针对复杂分割网络在小样本虹膜数据集上无法收敛的问题,提出一个基于轻量级卷积神经网络的虹膜分割模型.首先,该模型采用基于深度可分离卷积的特征提取模块提取虹膜图像特征,可在保持分割精度的同时显著减少模型参数;其次,在编码器和解码器之间引入一个高效的注意力机制模块,可有效获取丰富的上下文信息,并提高虹膜区域像素的可辨别性;最后,在虹膜数据库UBIRIS.V2上的实验结果表明,该方法不仅在小样本数据库上性能优势显著,且在大样本数据库上也具有较高的分割精度.
Aiming at the problem that complex segmentation networks could not converge on small sample iris datasets,we proposed an iris segmentation model based on lightweight convolutional neural network.Firstly,the model used a feature extraction module based on depth-wise separable convolution to extract iris image features,which could significantly reduce model parameters while maintaining segmentation accuracy.Secondly,an efficient attention mechanism module was introduced between the encoder and the decoder,which could effectively obtain rich context information and improve the discriminability of iris region pixels.Finally,the experimental results on the iris database UBIRIS.V2 show that the proposed method not only has significant performance advantages on small sample databases,but also has high segmentation accuracy on large sample databases.
作者
霍光
林大为
刘元宁
朱晓冬
袁梦
HUO Guang;LIN Dawei;LIU Yuanning;ZHU Xiaodong;YUAN Meng(School of Computer Science,Northeast Electric Power University,Jilin 132012,Jilin Province,China;College of Computer Science and Technology,Jilin University,Changchun 130012,China;Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,Jilin University,Changchun 130012,China)
出处
《吉林大学学报（理学版）》
CAS
北大核心
2023年第3期583-591,共9页
Journal of Jilin University:Science Edition
基金
吉林省教育厅科学技术研究项目(批准号:JJKH20220118KJ).
关键词
虹膜分割
深度学习
虹膜识别
小样本
轻量级
注意力机制
iris segmentation
deep learning
iris recognition
small sample
lightweight
attention mechanism
