A New Ridge-Features-Based Method for Fingerprint Image Quality Assessment

Abstract

Fingerprint is the most widely used biometric trait. Many factors may cause the quality degradation of fingerprint impressions: users, sensors and environmental facts. Most of the fingerprint-based biometric systems need an accurate prediction of fingerprint quality. A fingerprint quality measure can be used in enrollment or recognition stages, for improving the AFIS performances. In this work, a new fingerprint image quality estimation method guided by how experts classify fingerprint images quality is presented. By using six features, a continuous quality value is calculated. Experiments were performed in a well-known database. The proposed approach performance was evaluated by measuring its impact on the recognition stage and comparing it with the NFIQ quality algorithm. The Verifinger 4.2 was used as matching algorithm. The results shown that the proposed approach has a very good performance.

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

“…There are different scenarios to acquire contact-based fingerprints using various sensors. While the imaging techniques are advancing with sensor variations, the output of the fingerprint sensors are classified as (i) rolled full prints covering nail-to-nail area [ 11 , 12 ]; (ii) plain fingerprints covering flat regions [ 11 , 13 ]; (iii) live-scan swipe or partial fingerprints captured from portable devices [ 12 , 14 ]; and (iv) latent prints captured from crime scene surfaces [ 13 , 15 , 16 , 17 , 18 , 19 , 20 ]. Each acquisition mode can have different physical finger placement with the sensor surface and therefore exhibits various challenges which call for alternatives.…”

“…Contact-based fingerprint scanning systems occupy the larger portion of the state-of-the-art fingerprint recognition in civilian applications, while the contactless domain become attractive due to the presence of portable, compact and high-resolution cameras with different image capture strategies such as multispectral, multiview and 3D-image capture. While the imaging techniques are advancing with sensor variations, the input fingerprint images are categorized as: (i) rolled full prints, by covering the nail-to-nail region of the finger (low resolution) [ 11 , 12 ]; (ii) plain prints, by covering flat region of the finger [ 11 , 13 ]; (iii) partial prints, captured from portable devices (high resolution) [ 12 , 14 ]; (iv) latent prints, acquired from touch surfaces (high resolution) [ 13 , 15 , 16 , 17 , 18 , 19 , 20 ]; (v) multispectral [ 21 ]; and (vi) contactless (2D and 3D) images [ 3 ]. Figure 1 shows variations between such conventional contact-based and contactless fingerprints.…”