Person Identification Using Palm Print Features with an Efficient Method of DWT

• Published in: Global Trends in Information Systems and Software Applications pp. 337 - 346
• Main Authors: Sumathi, S., Rani Hemamalini, R.
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg
• Series: Communications in Computer and Information Science
• Subjects: Discrete Wavelet Transform; Identification; Palm print; Support Vector Machine
• ISBN: 3642292151; 9783642292156
• ISSN: 1865-0929; 1865-0937
• DOI: 10.1007/978-3-642-29216-3_37

In this paper, a new efficient method for individual identification, using palm print features based on Discrete Wavelet Transform (DWT) is proposed. Biometric system is designed to identify the people accurately, based on human physiological features. Palm print serves as reliable human identifier because the palm print patterns are not duplicated by others, even in monozygotic twins. Wavelet coefficients are used as features for identifying the individual and using Support Vector Machine (SVM) classifier for the classification purpose. Use reduced wavelet coefficients by specified window size placed at center of the image for palm print identification. Experiments are conducted for various window sizes and chose the best window size which gives good recognition rate and better result in substantial savings in storage and computation time. Experimental results show promising performance with the proposed methods from Hong Kong PolyU Multispectral Palm print database.