Presented at the 1997 IEEE Asilomar Conference on Signals, Systems, and Computers

A Fingerprint Classification Technique Using Directional Images

Meltem Ballan (1), F. Ayhan Sakarya (1), and Brian L. Evans (2)

(1) Department of Electronics and Telecommunication Engineering, Yildiz Technical University, 80750 Istanbul, Turkey - - Meltem's LinkedIn Page

(2) Department of Electrical and Computer Engineering, Engineering Science Building, The University of Texas at Austin, Austin, TX 78712-1084 USA

Paper - Slides


We present a fast, automated fingerprint classification technique based on the properties of singular points (delta and core point) in fingerprints obtained from directional histograms. The technique enhances the digitized image using adaptive clipping and image matching, finds the directional image by checking the orientations of individual pixels, computes directional histograms using overlapping blocks in the directional image, and classifies the fingerprint in to the Wirbel class (whorl and twin loop) or the Lasso class (arch, tented arch, right loop, and left loop. The new technique is simple, fast, and reliable.

A follow-up discussion to our paper is available.

Last Updated 01/23/14.