Fingerprint Matching Using Invariant Moment FingerCode and Learning Vector Quantization Neural Network

Jucheng Yang,Bungjun Min,Jongbin Park,Jinwook Shin,Dongsun Park

doi:10.1109/iccias.2006.294231

Fingerprint Matching Using Invariant Moment FingerCode and Learning Vector Quantization Neural Network

Jucheng Yang, Bungjun Min + Show 3 more

https://doi.org/10.1109/iccias.2006.294231

Copy DOI

Publication Date: Nov 1, 2006

Citations: 7

Affiliation: Jeonbuk National University

#Learning Vector Quantization Neural Network #Learning Vector Quantization + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

A novel method for fingerprint matching using invariant moment fingerCode and learning vector quantization (LVQ) neural network (NN) is proposed. A fingerprint image is preprocessed to remove the background and to enhance the image by eliminating the LL4 sub-band component of a hierarchical Discrete Wavelet Transform (DWT). Seven invariant moment features, called as a fingerCode, are extracted based on the reference point in the enhanced fingerprint image. Then a LVQ NN is trained with the feature vectors for matching. Experimental results show the proposed method has better performance with faster speed and higher accuracy comparing to the Gabor feature-based fingerCode method.

Full Text