Fingerprint Segmentation Algorithm Based on Fourier Transform

DOI

10.2991/itim-17.2017.5How to use a DOI?

Keywords

Fingerprint segmentation, Fast Fourier Transform (FFT), K-mean clustering, golden ratio

Abstract

On the basis of the study of the spectral characteristics of the fingerprint image, a fingerprint image segmentation algorithm based on Fourier transform is proposed. Fingerprint image is divided into blocks to calculate Fourier transform, the average value of the Fourier transform amplitude of the sub block image is accepted as the feature for segmentation. Using K-mean clustering to divide the feature into two categories, and the original fingerprint image is segmented. The experimental results show that the proposed algorithm has good adaptability to kinds of fingerprint images, and it can achieve satisfactory segmentation results. When the speed of the algorithm is pursuit, the fixed threshold which is constituted by golden ratio can be adopted, it can also achieve very good segmentation results.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiumei Cai
AU  - Mengge Song
PY  - 2017/08
DA  - 2017/08
TI  - Fingerprint Segmentation Algorithm Based on Fourier Transform
BT  - Proceedings of the 2017 International Conference on Information Technology and Intelligent Manufacturing (ITIM 2017)
PB  - Atlantis Press
SP  - 18
EP  - 22
SN  - 1951-6851
UR  - https://doi.org/10.2991/itim-17.2017.5
DO  - 10.2991/itim-17.2017.5
ID  - Cai2017/08
ER  -