A robust method for partial deformed fingerprints verification using genetic algorithm M.R. Girgis a , A.A. Sewisy b , R.F. Mansour b, * a Department of Computer Science, Faculty of Science, Minia University, Egypt b Department of Computer Science, Faculty of Computers and Information Sciences, Assiut University, Egypt Abstract Fingerprint verification is a well-researched problem, and automatic fingerprint verification techniques have been successfully adapted to both civilian and forensic applications for many years. However, this technology suffers from the problem of handling incomplete prints and often discards any partial fingerprints obtained. Recent research has begun to delve into the problems of incomplete or partial fingerprints. Genetic algorithm is developed to improvement of deformed ridges and complex distortions in fingerprints verification sys- tem. In order to deal with low quality fingerprint images. Experimental results demonstrate the robustness of our algorithm to other methods. And results show that the speed is raised using this method in the overall of the most optimum. Ó 2007 Elsevier Ltd. All rights reserved. Keywords: Genetic algorithm; Fingerprint matching; Fitness value; Graph minutiae; Optimization 1. Introduction Fingerprint matching is one of the most important stages in automatic fingerprint verification systems. This critical stage can be broadly classified as being minutiae- or correlation-based. Minutiae-based techniques attempt to align two sets of minutiae points and determine the total number of matched minutiae (Jain, Hong, & Bolle, 1997; Pernus, Kovacic, & Gyergyek, 1980). Correlation-based techniques, on the other hand, compare the global pattern of ridges and furrows to see if the ridges in the two finger- prints align (Bazen, Verwaaijen, Gerez, Veelenturf, & van der Zwaag, 2000; Sibbald, 1994). The performance of minutiae-based techniques rely on the accurate detection of minutiae points and the use of sophisticated matching techniques to compare two minutiae fields which undergo non-rigid transformations. The performance of correla- tion-based techniques is affected by non-linear distortions and noise present in the image. Many computer vision problems such as image extract- ing and matching can be cast as optimization problems. In this paper, genetic algorithm is developed to matching fin- gerprints based on lines extraction in fingerprints verifica- tion system, and use genetic algorithm (GA) as a tool to solve an object location (template matching) problem. The performance of automatic fingerprint verification algo- rithms depends on local ridge characteristics, because ridge direction and minutiae such as ridge endings and ridge bifurcations are used for matching shown in Fig. 1. Fingerprints have been used in identification of individ- uals for many years, because of the famous fact that each finger has a unique pattern. Many fingerprint identification and verification methods have been proposed, such as image correlation (Wilson, Watson, & Paek, 2000), graph matching (Isenor & Zaky, 1986), structural matching (Hre- chak & McHugh, 1990; Wahab, Chin, & Tan, 1998), and matching with transform features (Jain, Prabhakar, Hong, & Pankanti, 2000), and so on. Among them the most widely used one is methods based on point pattern match- ing (Ratha, Karu, Chen, & Jain, 1996). In recent years, new representations of fingerprint image and new matching 0957-4174/$ - see front matter Ó 2007 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2007.12.011 * Corresponding author. Tel.: +20 088 2289188. E-mail address: romanyf@aun.edu.eg (R.F. Mansour). www.elsevier.com/locate/eswa Available online at www.sciencedirect.com Expert Systems with Applications 36 (2009) 2008–2016 Expert Systems with Applications