Fingerprint Reference-Point Detection
- PDF / 4,786,844 Bytes
- 12 Pages / 600 x 792 pts Page_size
- 52 Downloads / 190 Views
Fingerprint Reference-Point Detection Manhua Liu School of Electrical & Electronic Engineering (EEE), Nanyang Technological University, Singapore 639798 Email: [email protected]
Xudong Jiang School of Electrical & Electronic Engineering (EEE), Nanyang Technological University, Singapore 639798 Email: [email protected]
Alex Chichung Kot School of Electrical & Electronic Engineering (EEE), Nanyang Technological University, Singapore 639798 Email: [email protected] Received 22 May 2004; Revised 20 August 2004; Recommended for Publication by Montse Pardas A robust fingerprint recognition algorithm should tolerate the rotation and translation of the fingerprint image. One popular solution is to consistently detect a unique reference point and compute a unique reference orientation for translational and rotational alignment. This paper develops an effective algorithm to locate a reference point and compute the corresponding reference orientation consistently and accurately for all types of fingerprints. To compute the reliable orientation field, an improved orientation smoothing method is proposed based on adaptive neighborhood. It shows better performance in filtering noise while maintaining the orientation localization than the conventional averaging method. The reference-point localization is based on multiscale analysis of the orientation consistency to search the local minimum. The unique reference orientation is computed based on the analysis of the orientation differences between the radial directions from the reference point, which are the directions of the radii emitted from the reference point with equivalent angle interval, and the local ridge orientations along these radii. Experimental results demonstrate that our proposed algorithm can consistently locate a unique reference point and compute the reference orientation with high accuracy for all types of fingerprints. Keywords and phrases: fingerprint recognition, fingerprint alignment, reference point, orientation smoothing, orientation consistency, reference orientation.
1.
INTRODUCTION
Fingerprint iscomposed of parallel ridgesand furrows on the tip of the finger. It is widely used for personal identification because of its easier accessibility, uniqueness, reliability, and low cost. Generally, there are two kinds of features for fingerprint recognition: global features such as the special ridge flow pattern and local features like minutia. Consistent extraction of these features is crucial for fingerprint recognition. However, pose transformation, that is, translation and rotation, usually exists in different fingerprint samples of the same finger. One popular solution is to consistently locate a unique reference point and compute a unique reference orientation for translational and rotational alignment of different samples. The singular points, that is, core and delta points (see Figure 1a), are unique landmarks of fingerprint, where the ridge curvature is higher than other areas and the orientation changes rapidly. They are usually used as reference
Data Loading...
