The Use of Two Transform Methods in Fingerprints Recognition
AbstractFinger prints are the oldest and most widely used form of biometric identification. Despite the widespread use of fingerprints, there is little statistical theory on the uniqueness of fingerprint minutiae. Fingerprint matching is the process used to determine whether two sets of fingerprint ridge detail come from the same finger. There exist multiple algorithms that do fingerprint matching in many different ways. Some methods involve matching minutiae points between the two images, In this paper used median filter to enhance the images, and then use DCT (Discrete Cosine Transform) and FDCvT Via Wrapping to compute the feature extraction from the images. The Template Matching can be applied by finding the more similar values between the original image and the template.The proposed system includes two stages: first stage is implemented by taking individual natural fingerprint images with several positions and calculation of the features vector (Mean and standard deviation) by using FDCvT via Wrapping and DCT. The second stage is implemented by taking several samples of new fingerprint images for testing the work. The results show that the fingerprints Recognition rate by the (FDCvT via Wrapping and DCT) achieves better recognition rate (84%).
- Fingerprint Recognition --- DCT --- Curvelet Transform --- FDCvT Via Wrapping.
- Article View: 79
- PDF Download: 177