GLCM Inspired Fingerprints Segmentation Algorithm with Adaptive Block Size

In order to reduce the dependence on the images' sizes, resolutions and qualities, a self-adaptive block size fingerprint segmentation algorithm based on the gray level co-occurrence matrix (GLCM) is proposed. Firstly, the image is divided into a number of non-overlapped rectangular blocks whos...

Full description

Saved in:
Bibliographic Details
Published inApplied Mechanics and Materials Vol. 239-240; pp. 1456 - 1461
Main Authors Luo, Jun Li, Li, Hui Na
Format Journal Article
LanguageEnglish
Published Zurich Trans Tech Publications Ltd 01.01.2013
Subjects
Adaptive Block Size
Contrast Variance
Fingerprint Image Segmentation
GLCM
Online AccessGet full text

Cover

More Information
Summary:In order to reduce the dependence on the images' sizes, resolutions and qualities, a self-adaptive block size fingerprint segmentation algorithm based on the gray level co-occurrence matrix (GLCM) is proposed. Firstly, the image is divided into a number of non-overlapped rectangular blocks whose size is automatically determined by the mean of the ridge distance from the spectrogram. Then the contrasts of the GLCM of each block in different directions of pixel-pair could be calculated. Since the variances of these contrasts are different for the foreground and the background, finally, the fingerprint image can be segmented correctly. Experimental results show that the proposed algorithm performs effectively in processing images gathered by various fingerprint sensors in diverse environments.
Bibliography:Selected, peer reviewed papers from the 2012 International Conference on Measurement, Instrumentation and Automation (ICMIA 2012), September 15-16, 2012, Guangzhou, China
ISBN:9783037855454
3037855452
ISSN:1660-9336
1662-7482
1662-7482
DOI:10.4028/www.scientific.net/AMM.239-240.1456