Authors: Abdelwahed Motwakel; Adnan Shaout; Gasm Elseed Ibrahim Mohamed
Addresses: College of Post Graduate Studies, Sudan University of Science and Technology, Sudan ' The Electrical and Computer Engineering Department, The University of Michigan, Dearborn, USA ' International University of Africa, P.O. Box 2469, Khartoum, Sudan
Abstract: The quality of a fingerprint image greatly affects the performance of minutiae extraction and the process of matching in fingerprint identification systems. In order to improve the performance of the fingerprint identification system, a fuzzy morphology technique is proposed in this paper to enhance dry fingerprint images. The proposed method follows three steps; smoothing, fuzzy dilation, and union operation. Experimental results, using the db_its_2009 database, private database collected by the Department of Electrical Engineering, Institute of Technology Sepuluh Nopember, Surabaya, Indonesia, indicate that the proposed method improves the quality of fingerprint images, thus, improving the performance of the fingerprint identification system significantly.
Keywords: dry fingerprint images; fuzzy morphology; smoothing; fuzzy dilation; image enhancement; dry fingerprints; fuzzy logic; fingerprint identification systems; biometrics.
International Journal of Knowledge Engineering and Data Mining, 2016 Vol.4 No.1, pp.40 - 53
Received: 04 Jul 2016
Accepted: 14 Oct 2016
Published online: 06 Feb 2017 *