Automatic Fingerprint Matching Using Extended Feature Set

• NCJ Number: 235577
• Author(s): Anil K. Jain
• Date Published: August 2010
• Length: 66 pages
• Grant Number(s): 2007-RG-CX-K183
• Agencies: NIJ-Sponsored
• Publication Type: Report (Study/Research)
• Award: Automatic Fingerprint Matching Using Extended Feature Set

Annotation

This study developed algorithms for encoding and matching extended fingerprint features, created fusion algorithms to combine extended features with minutiae information so as to improve fingerprint matching accuracy, and examined the contributions of various extended features in latent fingerprint matching.

Abstract

Fingerprint friction-ridge features are generally described in a hierarchical order at three different levels: 1evel 1 (ridge flow), 1evel 2 (minutiae points), and 1evel 3 (pores and ridge shape, etc.). Current automated fingerprint Identification Systems (AFIS) generally rely only on a subset of level 1 and level 2 features for matching. On the other hand, latent print examiners often take advantage of a much richer set of features that naturally occur in fingerprints. Fingerprint features, other than minutiae and core/delta, are also referred to as the extended feature set. The experiments conducted determined that almost all the extended features of fingerprints produce some improvement in latent matching accuracy. In addition, extended features at a higher level are more effective in improving latent match accuracy than those at a lower level. Another finding is that high image resolution (at least 1,000 ppi) is necessary, but not sufficient for reliably capturing level 3 features. Based on study findings, the author recommends that extended features at level 1 and level 2 be incorporated into AFIS. Another recommendation is that GUI tools be developed in order to help fingerprint examiners manually mark extended features (especially ridge skeleton) at level 1 and level 2 in latent prints. The author also advises that it is critical to improve the quality of enrolled fingerprints so that a sufficient number of level 3 features can be extracted before level 3 features can have an important role in AFIS. 8 figures and 11 references