Fingerprint recognition using neural networks / Kennie Yeoh Eng Hoe

Traditional methods of fingerprint verification uses either complicated feature detection algorithms that are not specific to each fingerprint, or compare two fingerprint images directly using image processing toots. The former involves very complicated calculations and tedious algorithms, and the l...

Full description

Saved in:
Bibliographic Details
Main Author: Kennie Yeoh , Eng Hoe
Format: Thesis
Published: 2001
Subjects:
Online Access:http://studentsrepo.um.edu.my/13528/4/Kennie_Yeoh_Eng_Hoe.pdf
http://studentsrepo.um.edu.my/13528/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditional methods of fingerprint verification uses either complicated feature detection algorithms that are not specific to each fingerprint, or compare two fingerprint images directly using image processing toots. The former involves very complicated calculations and tedious algorithms, and the latter tend to work poorly. In this paper it is described a new method which takes the middle ground. This paper studies the implementation of the Fast Fourier Transform and Artificial Neural Networks into the recognition of fingerprints. With tests conducted on the implementation of the Fourier Transform as a method of fingerprint feature extraction, the use of the Fourier Transform was proven not to work. Alternatively, patch-matching algorithm was developed in success of the Fourier Transform method when results -were not favorable to it. A flow of the process goes from fingerprint acquisition using inkpads and a scanner, followed by image pre-processing steps to produce cleaner more visually acceptable images. Next, features are extracted from the fingerprint and later fed into neural networks for recognition. This project aims at producing a system study on various factors that need to be taken into consideration for fingerprint recognition, from response time, to stringency levels and of course, accurate recognition of verified fingerprints.