An Improved Approach in Fingerprint Recognition Algorithm
There are several reasons like displacement of finger during scanning, environmental conditions, behavior of user, etc., which causes the reduction in acceptance rate during fingerprint recognition. The result and accuracy of fingerprint recognition depen
- PDF / 447,948 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 43 Downloads / 238 Views
Abstract There are several reasons like displacement of finger during scanning, environmental conditions, behavior of user, etc., which causes the reduction in acceptance rate during fingerprint recognition. The result and accuracy of fingerprint recognition depends on the presence of valid minutiae. This paper proposed an algorithm, which identify the valid minutiae and increase the acceptance rate and accuracy level. The work of the proposed algorithm is categorized into two parts: preprocessing and post-processing. The proposed algorithm enhanced most of the phases of preprocessing for removing the noise, and make the clear fingerprint image for feature extraction and enhanced the post-processing phases for eliminating the false extracted minutiae, to extract exact core point detection, and matching valid minutiae. The developed proposed algorithm is tested using FVC2000 and FingerDOS databases for measuring the average FMR = 1% and FNMR = 1.43% and accuracy 98.7% for both databases. Keywords Orientation estimation recognition
Image enhancement Thinning Fingerprint
1 Introduction To identify an authorized person is the vital task in the world of internet. Password-based and ID-based authentications are traditional approach, which becomes incompetent to suit the high-security requirements applications like ATM M. B. Patel (&) S. M. Parikh A.M.Patel Institute of Computer Studies, Ganpat University, Gujarat, India e-mail: [email protected] S. M. Parikh e-mail: [email protected] A. R. Patel Florida Polytechnic University, Lakeland, FL, USA e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2019 A. K. Luhach et al. (eds.), Smart Computational Strategies: Theoretical and Practical Aspects, https://doi.org/10.1007/978-981-13-6295-8_12
135
136
M. B. Patel et al.
machines, cash terminals, access control system, and so on. Biometric-based authentication substitutes the traditional approaches. It verifies and identifies an individual based on his behavioral and physiological biometric data. As per historical data, the fingerprint recognition systems are used by every forensic and low enforcement agency. Nowadays, government programs and services are integrated with biometrics and become a creator and consumer of biometric technology, as well as, it is used in civilian and commercial applications because of cheaper, small capture device, and robust development of fingerprint recognition system [1]. A fingerprint image contains mainly two types of features: ridge flow information and minutiae. In fingerprint image, ridge flow information is defined by the ridges and valleys pattern. The minutiae are mainly referred to as ridge ending and ridge bifurcation, which contains the disconnection in fingerprint impression. There are overall 150 types of minutiae types identified. In the analysis of fingerprints, the ridge flow information and minutiae play a vital role in showing that the two fingers are not the same. In a full fingerprint, average 70–150 minutiae are there. The numbers of minutiae
Data Loading...
