Share Email Print
cover

Proceedings Paper

Research on 3D fingerprint structure recognition based on OCT system
Author(s): Wang Liu; Zhaowei Zhong; Zhifang Li; Yongping Lin; Hui Li
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The most widely used fingerprint recognition technology is to extract the texture information and features of the skin fingerprint, and then use the algorithm to match and identify, and finally confirm the identity. However, when there are dirt and water stains on the fingerprint of the skin, or when the fingerprint skin is worn or even peeled off, the generation of these factors will bring difficulties to the identification system. In this study, optical coherence tomography (OCT) was used to obtain the three-dimensional structure of the finger fingerprint, and the three-dimensional structure inside the fingerprint was identified. The three-dimensional structure image of the fingerprint obtained by the OCT system can not only observe the fingerprint skin information, but also acquire the image information of the internal structure of the fingerprint. Taking the acquired three-dimensional structure image of fingerprint as the research object, a three-dimensional convolutional neural network model is constructed based on the theory of deep learning, and the features of image data is extracted and trained to achieve the purpose of recognition.

Paper Details

Date Published: 12 March 2020
PDF: 8 pages
Proc. SPIE 11434, 2019 International Conference on Optical Instruments and Technology: Optical Systems and Modern Optoelectronic Instruments, 1143417 (12 March 2020); doi: 10.1117/12.2549931
Show Author Affiliations
Wang Liu, Fujian Normal Univ. (China)
Zhaowei Zhong, Fujian Normal Univ. (China)
Zhifang Li, Fujian Normal Univ. (China)
Yongping Lin, Fujian Normal Univ. (China)
Hui Li, Fujian Normal Univ. (China)


Published in SPIE Proceedings Vol. 11434:
2019 International Conference on Optical Instruments and Technology: Optical Systems and Modern Optoelectronic Instruments
Juan Liu; Baohua Jia; Xincheng Yao; Yongtian Wang; Takanori Nomura, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray