Neural-based quality measurement of fingerprint images in contactless biometric systems

Traditional fingerprint biometric systems capture the user fingerprint images by a contact-based sensor. Differently, contactless systems aim to capture the fingerprint images by an approach based on a vision system without the need of any contact of the user with the sensor. The user finger is placed in front of a special CCD-based system that captures the pattern of ridges and valleys of the fingertips. This approach is less constrained by the point of view of the user, but it requires much more capability of the system to deal with the focus of the moving target, the illumination problems and the complexity of the background in the captured image. During the acquisition procedure, the quality of each frame must be carefully evaluated in order to extract only the correct frames with valuable biometric information from the sequence. In this paper, we present a neural-based approach for the quality estimation of the contactless fingertips images. The application of the neural classification models allowed for a relevant reduction of the computational complexity permitting the application in realtime. Experimental results show that the proposed method has an adequate accuracy, and it can capture fingerprints at a distance up to 0.2 meters.