摘要
针对虹膜活体检测中的特征提取问题,提出一种基于深度卷积神经网络的虹膜活体检测算法。通过归一化、分块归一化和直接切取方式对虹膜图像进行预处理,利用卷积神经网络提取经预处理的虹膜图像特征,使用训练分类器对真伪虹膜进行分类。实验结果表明,该算法能自动学习虹膜图像的隐藏特征,使真实虹膜和伪造虹膜的特征更具区分性,并且在ND-Contact和CASIA-Iris-Fake数据库中获得96.72%以上的检测正确率。
In view of iris liveness detection of feature extraction, this paper proposes an iris liveness detection algorithm based on deep Convolutional Neural Network （CNN）. Three modes of iris regions including normalization, block normalization and cutting directly are used to preprocess iris image, and they are suggested as the input of CNN for extracting features, then genuine and fake irises are identified with trained classifier. Experimental results show that this algorithm can learn the hidden characteristics of iris image automatically, make it more discriminative between genuine and fake iris feature,and it achieves above 96.72% accuracy on ND-Contact and CASIA-Iris-Fake database.
出处
《计算机工程》
CAS
CSCD
北大核心
2016年第5期239-243,248,共6页
Computer Engineering
基金
河西学院青年教师科研基金资助项目(QN2014-25)
关键词
生物特征识别
虹膜识别
虹膜活体检测
卷积神经网络
自动特征学习
biometric feature recognition
iris recognition
iris liveness detection
Convolutional Neural Network（CNN）
automatic feature learning
作者简介
李志明（1980-），男，讲师、硕士，主研方向为计算机视觉。
