DORSAL HAND VEIN PATTERN AUTHENTICATION BY HOUGH PEAKS

The quest of providing more secure identification system has led to rise in developing biometric systems. Biometrics such as face, fingerprint and iris have been developed extensively for human identification purpose and also to provide authentic input to many security systems in the past few decades. Dorsal hand vein pattern is an emerging biometric which is unique to every individual. In this paper Linear Hough transform is used to extract the features of query and data base images. K-Nearest neighbor Search is used to obtain best match between query image and database. The extraction of the vein patterns was obtained by morphological techniques. Noise reduction filters are used to enhance the vein patterns.

[1]  Ahmed M. Badawi.  Hand Vein Biometric Verification Prototype: A Testing Performance and Patterns Similarity , 2006, IPCV.

[2]  Yunhong Wang,et al.  Extracting Hand Vein Patterns from Low-Quality Images: A New Biometric Technique Using Low-Cost Devices , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).

[3]  Chih-Lung Lin,et al.  Biometric verification using thermal images of palm-dorsa vein patterns , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Soo-Won Kim,et al.  Improved vein pattern extracting algorithm and its implementation , 2000 .

[5]  Daniel T. Larose,et al.  k‐Nearest Neighbor Algorithm , 2005 .

[6]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[7]  T. Tanaka,et al.  Biometric authentication by hand vein patterns , 2004, SICE 2004 Annual Conference.

[8]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.