An Improved K-Means Based Method for Fingerprint Segmentation with Sensor Interoperability

Fingerprint segmentation is an important step in an automatic fingerprint recognition system. Due to applications of various sensors, fingerprint segmentation inevitably suffers from sensor interoperability problem. K-means algorithm is one solution to address the sensor interoperability problem in fingerprint segmentation. However, the traditional k-means based method does not well deal with the border between the foreground and the background. The over-segmentation of foreground area may appear and some important minutiae are lost. To effectively address the issue, we propose an improved k-means based segmentation method with sensor interoperability called ISKI. ISKI performs the secondary determination to the blocks which have similar distances with the two cluster centers after k-means clustering. The proposed method is applied on a number of fingerprint databases which are collected by various sensors. Experimental results show our proposed method significantly improves the accuracy of segmentation.

[1]  Jiawei Han,et al.  Data Mining: Concepts and Techniques, Second Edition , 2006, The Morgan Kaufmann series in data management systems.

[2]  Petra Perner,et al.  Data Mining - Concepts and Techniques , 2002, Künstliche Intell..

[3]  Gongping Yang,et al.  -Means Based Fingerprint Segmentation with Sensor Interoperability , 2010, EURASIP J. Adv. Signal Process..

[4]  Yilong Yin,et al.  Personalized Fingerprint Segmentation , 2009, ICONIP.

[5]  Arun Ross,et al.  Biometric Sensor Interoperability: A Case Study in Fingerprints , 2004, ECCV Workshop BioAW.

[6]  Xuejun Yang,et al.  Two steps for fingerprint segmentation , 2007, Image Vis. Comput..

[7]  M.U. Akram,et al.  Improved fingerprint image segmentation using new modified gradient based technique , 2008, 2008 Canadian Conference on Electrical and Computer Engineering.

[8]  Anil K. Jain,et al.  Handbook of Fingerprint Recognition , 2005, Springer Professional Computing.

[9]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[10]  Yilong Yin,et al.  Fingerprint Image Segmentation Based on Quadric Surface Model , 2005, AVBPA.

[11]  Xinjian Chen,et al.  Segmentation of Fingerprint Images Using Linear Classifier , 2004, EURASIP J. Adv. Signal Process..

[12]  Babu M. Mehtre,et al.  Segmentation of fingerprint images using the directional image , 1987, Pattern Recognit..

[13]  Venu Govindaraju,et al.  Robust Point-Based Feature Fingerprint Segmentation Algorithm , 2007, ICB.

[14]  Sabih H. Gerez,et al.  Segmentation of Fingerprint Images , 2001 .

[15]  Gongping Yang,et al.  Feature selection for sensor interoperability: A case study in fingerprint segmentation , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.