Detecting Altered Fingerprints

Abstract

Abstract-The widespread deployment of Automated Fingerprint Identification Systems (AFIS) in law enforcement and border control applications has prompted some individuals with criminal background to evade identification by purposely altering their fingerprints. Available fingerprint quality assessment software cannot detect most of the altered fingerprints since the implicit image quality does not always degrade due to alteration. In this paper, we classify the alterations observed in an operational database into three categories and propose an algorithm to detect altered fingerprints. Experiments were conducted on both real-world altered fingerprints and synthetically generated altered fingerprints. At a false alarm rate of 7%, the proposed algorithm detected 92% of the altered fingerprints, while a well-known fingerprint quality software, NFIQ, only detected 20% of the altered fingerprints.

On separating overlapped fingerprints

“…Manual marking of singular points is a common practice in latent fingerprint community [4]. As proposed in [26], a fingerprint orientation field can be decomposed into singular orientation field and continuous orientation field (13) The singular orientation field is defined by the Zero-Pole model proposed by Sherlock and Monro [27] as (14) where , are the core and delta points in the fingerprint. The continuous orientation field is defined by (15) Note that the continuous orientation field is smooth everywhere.…”

On matching altered fingerprints

“…However, large-scale fingerprint identification systems are facing a growing threat due to fingerprint alteration since, compared to other biometric modalities (e.g., face and iris), it is relatively easier to obfuscate or alter fingerprints. Previous work on this topic [8,13] addressed the automatic detection of altered fingerprints based on the abnormality in orientation field and minutiae distribution. Figure 10.…”

“…Fingerprints submitted to AFIS need to pass through an altered fingerprint detector at the front end of the fingerprint matching process. Abnormality in orientation field and minutiae distribution in altered fingerprints provide indication of possible alterations [8,13]. Once the altered fingerprints are detected, the suspect is sent to a secondary inspection in order to verify (i) that the unusual fingerprint pattern is indeed due to alteration, and (ii) whether these altered fingerprints could still be matched to the suspect's pre-altered fingerprints possibly contained in the databases.…”

A Challenge to Analyze and Detect Altered Human Fingerprints

“…What we are doing is we are integrating image with ID number to extract the details of the person with criminal record along with altered [3][5] and non-altered fingerprint images.…”