Comparison of cross-correlation and ring-wedge feature extraction in fingerprint recognition

Authors

Astra Kristina B. Mallari ⋅ PH National Institute of Physics, University of the Philippines Diliman
Maricor N. Soriano ⋅ PH National Institute of Physics, University of the Philippines Diliman
Caesar A. Saloma ⋅ PH National Institute of Physics, University of the Philippines Diliman

Abstract

We compare the success rate of discrimination of 100 in-class and out-of-class database fingerprints by cross-correlation and by ring-wedge feature extraction. Cross-correlation was done by getting correlation peak values for test and target prints, while ring-wedge features were used to classify the prints using the least-squares method. Ring-wedge sampling was seen to classify in-class fingerprints better, with a recognition accuracy of 82.11%, against 26.32% for correlation.

Downloads

Issue

2002: Proceedings of the 20th Samahang Pisika ng Pilipinas Physics Congress

Article ID

SPP-2002-PP-26

Section

Image and Signal Processing

Published

2002-10-23

How to Cite

[1]

AKB Mallari, MN Soriano, and CA Saloma, Comparison of cross-correlation and ring-wedge feature extraction in fingerprint recognition, Proceedings of the Samahang Pisika ng Pilipinas 20, SPP-2002-PP-26 (2002). URL: https://proceedings.spp-online.org/article/view/SPP-2002-PP-26.