A finger vein recognition algorithm based on deep learning. (2017)

• Record Type: Journal Article
• Authors: Chen, Cheng; Wu, Zhendong; Zhang, Jianwu; Li, Ping; Azmat, Freeha
• Is Part Of: International journal of embedded systems. Volume 9:Number 3(2017)
• Page Start: 220
• Page End: 228
• Publication Date: 2017
• Subjects: feature block fusion -- FBF -- deep belief network -- DBN -- convolution neural network -- finger vein recognition; Embedded computer systems -- Periodicals; 004.16
• Languages: English
• ISSNs: 1741-1068

Abstract

Deep learning has recently achieved impressive performance in the area of biometric recognition. The technology of finger vein recognition possesses better anti forgery performance and identification stability in collecting and certificating information of human bodies. The traditional finger vein recognition method is mainly based on template matching or whole feature recognition, suffering from light instability of the acquisition equipment which leads to low robustness. In this paper, we adapt a finger vein recognition algorithm using feature block fusion and deep belief network (FBF-DBN) and a convolutional neural network (CNN), then we combine these two network systems to judge the performance of our system. Meanwhile, we improve deep network input by using feature points set in vein images, effectively reducing the time in learning and detection, meeting the practical needs of biometric recognition specifically applied to embedded equipment. The experiment results showed that FBF-DBN and CNN algorithm present better recognition performance and faster speed.