Please use this identifier to cite or link to this item: https://hdl.handle.net/1959.11/4658
Title: Learning framework for examiner-centric fingerprint classification using spectral features
Contributor(s): Kwan, Paul Hing  (author); Guo, Yi (author); Gao, Junbin (author)
Publication Date: 2007
DOI: 10.1117/12.749777
Handle Link: https://hdl.handle.net/1959.11/4658
Abstract: In recent years, the tasks of fingerprint examiners have been greatly aided by the development of automatic fingerprint classification systems. These systems operate by matching low-level features automatically extracted from fingerprint images, often represented collectively as numeric vectors, for their decision. However, there are two major shortcomings in current systems. First, the result of classification depends solely on the chosen features and the algorithm that matches them. Second, the systems cannot adapt their results over time through interaction with individual fingerprint examiners who often have different degrees of experiences. In this paper, we demonstrate by incorporating relevance feedback in a fingerprint classification system, a personalized semantic space over the database of fingerprints for each user can be incrementally learned. The fingerprint features that induce the initial features space from which individual semantic spaces are being learned were obtained by multispectral decomposition of fingerprints using a bank of Gabor filters. In this learning framework, the out-or-sample extension of a recently introduced dimensionality reduction method, called Twin Kernel Embedding (TKE), is applied to learn both the semantic space and a mapping function for classifying novel fingerprints. Experimental results confirm this learning framework for examiner-centric fingerprint classification.
Publication Type: Conference Publication
Conference Details: MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition, Wuhan, China, 15th - 17th November, 2007
Source of Publication: MIPPR 2007: Pattern Recognition and Computer Vision & The 5th International Symposium on Multispectral Image Processing and Pattern Recognition, v.6788 p.67881H
Publisher: International Society for Optical Engineering (SPIE)
Place of Publication: Washington, United States of America
Fields of Research (FoR) 2008: 080109 Pattern Recognition and Data Mining
Socio-Economic Objective (SEO) 2008: 890201 Application Software Packages (excl. Computer Games)
Peer Reviewed: Yes
HERDC Category Description: E1 Refereed Scholarly Conference Publication
Appears in Collections:Conference Publication

Files in This Item:
2 files
File Description SizeFormat 
Show full item record

Page view(s)

1,234
checked on Mar 3, 2024
Google Media

Google ScholarTM

Check

Altmetric


Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.