03.2021.13.20

Wavelet feature extraction of Area Fingerprint Scanners Authentication

Author(s):

Esraa H. Abdul Ameer†, Zahraa Faisal‡, Nora H. Sultan†

Affiliation(s):

†Department of Computer Science, College of Education for Girls, University of Kufa, Najaf, Iraq
‡ Department of Quality Assurance & Performance Evaluation, Kufa University, Iraq

Corresponding Author Email: lsntl@ccu.edu.tw

This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

This paper is concerned with the study and design of a fingerprint recognition system based on wavelet transformation. Fingerprints of 100- persons were taken as test data. These fingerprints were scaled, rotated and translated accordingly and compared with the original images. The system proved to be successful in the presence of these effects, where. The improve the feature extraction and recognition rate of the system, texture features were extracted from spatial domain and combined with the wavelet features. The selected texture features are well known for their capability to recognize images in general. The recognition accuracy, after the combination, was highly improved. It gives about 100% for the conditions covered in the tests. In the case of recognizing multiple instances for the same person, the results show that wavelet descriptors can be efficient representation (when compared with moment descriptors) and can provide reliable recognition in problems with large input variability.