Study of Fingerprint Image Feature Extraction Algorithm

Abstract:

Fingerprint image feature extraction is a critical step to fingerprint recognition system, which studies topological structure, mathematical model and extraction algorithm of fingerprint feature. This paper presents system design and realization of feature extraction algorithm for fingerprint image. On the basis of fingerprint skeleton image, feature points including ending points, bifurcation points and singular points are extracted at first. Then false feature points are detected and eliminated by the violent changes of ambient orientation field. True feature points are marked at last. Test result shows that the method presented has good accuracy, quick speed and strong robustness for realtime application.

• Periodical: Applied Mechanics and Materials (Volumes 519-520)
• Pages: 577-580
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.519-520.577
• Online since: February 2014
• Authors: Shuai Yuan*, Guo Yun Zhang, Jian Hui Wu, Long Yuan Guo
• Keywords: Bifurcation Point, Ending Point, Feature Extraction, Fingerprint Image, Orientation Field, Singular Points, Topological Structure

References

[1] Meixian Feng, Hongmei Yuan: Study of fingerprint feature extraction algorithm. Journal of Daqing Normal University. Vol. 5 (2008), pp.1-4 (In Chinese).

[2] Feng Xu, Sidan Du, Duntang Gao: Local ridges characteristics based direct gray-scale minutiae detection in fingerprints. Journal of Microprocessors. Vol. 2 (2006), pp.37-40 (In Chinese).

[3] Feng Xu, Yanli Sun: Fingerprint minutiae extraction based on orientation filtering. Journal of Silicon Valley. Vol. 9 (2009), pp.58-59 (In Chinese).

[4] Yingding Zhao, Shiming Dai, Jingang Liu: Research on grey-scale image based extraction fingerprint minutiae algorithm. Journal of System Simulation. Vol. 2 (2006), pp.319-322 (In Chinese).