A Novel 2D Feature Extraction Method for Fingerprints Using Minutiae Points and Their Intersections

Nibras Ar Rakib, SM Zamshed Farhan, Md Mashrur Bari Sobhan, Jia Uddin, Arafat Habib

Abstract


The field of biometrics has evolved tremendously for over the last century. Yet scientists are still continuing to come up with precise and efficient algorithms to facilitate automatic fingerprint recognition systems. Like other applications, an efficient feature extraction method plays an important role in fingerprint based recognition systems. This paper proposes a novel feature extraction method using minutiae points of a fingerprint image and their intersections. In this method, initially, it calculates the ridge ends and ridge bifurcations of each fingerprint image. And then, it estimates the minutiae points for the intersection of each ridge end and ridge bifurcation. In the experimental evaluation, we tested the extracted features of our proposed model using a support vector machine (SVM) classifier and experimental results show that the proposed method can accurately classify different fingerprint images.

Keywords


feature extraction, fingerprint images, minutiae points, support vector machine,

Full Text:

PDF


DOI: http://doi.org/10.11591/ijece.v7i5.pp2547-2554
Total views : 295 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.