skip navigation

Justinfo Subscribe to Stay Informed

Add your conference to our Justice Events calendar


NCJRS Abstract


Subscribe to Stay Informed
Want to be in the know? JUSTINFO is a biweekly e-newsletter containing information about new publications, events, training, funding opportunities, and Web-based resources available from the NCJRS Federal sponsors. Sign up to get JUSTINFO in your inbox.

The document referenced below is part of the NCJRS Library collection.
To conduct further searches of the collection, visit the NCJRS Abstracts Database.

How to Obtain Documents
NCJ Number: NCJ 227931   Add to Shopping cart   Find in a Library
Title: Extended Feature Set and Touchless Imaging for Fingerprint Matching
  Document URL: PDF 
Author(s): Yi Chen
Date Published: 06/2009
Page Count: 209
  Annotation: This study addressed two critical issues related to the transition from manual fingerprint matching to the use of biometric technology: the failure of automatic systems to make full use of the knowledge gained from manual fingerprint matching and the failure of automatic systems to fully achieve interoperability between advanced sensing technology and legacy fingerprint databases.
Abstract: Regarding the first issue, the study found automatic systems have not fully used the knowledge gained by forensic experts in manual fingerprint matching regarding extended fingerprint features, namely, ridge skeletons, pores, incipients, and dots. The current study proposes methods to automatically extract and compare these extended features in a hierarchical fashion. Using these methods, experiments showed improvement in both live-scan and latent matching after extended features were incorporated. In developing the proposed methods, researchers conducted statistical analysis on the reproducibility and individuality of the extended features of fingerprints and demonstrated their distinctive nature both theoretically and empirically. In addressing the second issue, researchers investigated the interoperability between a new fingerprint sensing technology based on touchless imaging and the legacy rolled-fingerprint data. This led to the development of a nonparametric virtual rolling method that unwraps the three-dimensional touchless fingerprints into two-dimensional rolled-equivalent fingerprints. Researchers also developed a quality measure and an enhancement algorithm for touchless fingerprints. Experiments on a small database with 102 fingers showed the effectiveness of the proposed methods in achieving compatibility in matching touchless fingerprints with legacy rolled fingerprints. This report also proposes future research on extended fingerprint features and sensor interoperability. Extensive figures, tables, and mathematical formulas, and a 136-item bibliography
Main Term(s): Criminology
Index Term(s): Fingerprints ; Automated fingerprint processing ; Suspect identification ; Forensics/Forensic Sciences ; Investigative techniques ; NIJ final report
Sponsoring Agency: National Institute of Justice (NIJ)
US Department of Justice
Office of Justice Programs
United States of America
Grant Number: 2007-DN-BX-0005
Sale Source: National Institute of Justice/NCJRS
Box 6000
Rockville, MD 20849
United States of America
Type: Report (Study/Research)
Country: United States of America
Language: English
  To cite this abstract, use the following link:

* A link to the full-text document is provided whenever possible. For documents not available online, a link to the publisher's web site is provided.