Quality measurement of unwrapped three-dimensional fingerprints: A neural networks approach

Abstract

Traditional biometric systems based on the fingerprint characteristics acquire the biometric samples using touch-based sensors. Some recent researches are focused on the design of touch-less fingerprint recognition systems based on CCD cameras. Most of these systems compute three-dimensional fingertip models and then apply unwrapping techniques in order to obtain images compatible with biometric methods designed for images captured by touch-based sensors. Unwrapped images can present different problems with respect to the traditional fingerprint images. The most important of them is the presence of deformations of the ridge pattern caused by spikes or badly reconstructed regions in the corresponding three-dimensional models. In this paper, we present a neural-based approach for the quality estimation of images obtained from the unwrapping of three-dimensional fingertip models. The paper also presents different sets of features that can be used to evaluate the quality of fingerprint images. Experimental results show that the proposed quality estimation method has an adequate accuracy for the quality classification. The performances of the proposed method are also evaluated in a complete biometric system and compared with the ones obtained by a well-known algorithm in the literature, obtaining satisfactory results.

Biometrics in the World of Electronic Borders

“…They can secure the integrity and preventive access of fingerprints would be a positive direction in the step to deal with the problem posed by acquisition of data. Many sensors demand to move the finger over the buying surface for several seconds, and then wait for a frame to be of acceptable quality to avoid speed of data collection problems [22], [23].…”

Automated Border Control Systems: Biometric Challenges and Research Trends

“…Moreover, the illumination must be uniform and able to compensate for environmental variations [78]. -Higher quality fingerprint images also increase the performance of fingerprint recognition technologies, and can be obtained by enhancing both the usability of the system and the algorithms for the quality estimation [28,38,24], without increasing the acquisition time. -Less-intrusive iris recognition techniques could help in extending the field of use iris-based systems, since they are currently the most accurate, but have high costs and intrusiveness.…”