عنوان المقالة:تمييز بصمة الاصبع باستخدام تحويل هار الموجي وخصائص الخطوط المحلية فقط Fingerprint Recognition Using Haar Wavelet Transform and Local Ridge Attributes Only
ميلا غازي عبد الحليم، د. لؤي ادور جورج ، هدى مصطفى البياتي
English Authors
Mela G. Abdul-Haleem, Loay E. George, Huda M. Al-Bayti
Abstract
Abstract— Many of the existing human recognition applications are based on fingerprints. Most of fingerprint techniques use minutiae points for fingerprint representation and matching. Moreover, the techniques are mostly failed when partial fingerprint images are matched. This paper proposes a fingerprint recognition technique which uses local robust features for fingerprint representation and matching. The technique performs well in presence of partial fingerprints. The adopted local features include features extracted from the detail of Haar wavelet subheads. Experiments are performed using a database of 160 low quality fingerprint images collected from 40 subjects, (i.e., 4 images per subject). The test results indicated good system ability to signify low-quality fingerprint images even with existence of partial loss in fingerprint images. The technique has produced a recognition accuracy of 94.37% using one decomposition level and 96.87% using two decomposition levels of wavelet.
Publication Date
1/15/2014
Publisher
International Journal of Advanced Research in Computer Science and Software Engineering
ميلا غازي عبد الحليم | Mela G. Abdul-Haleem | 5458