Fingerprint Image Quality Estimation

Fingerprints have been used for manual personal identification for centuries. Recent advances in ink less image capture devices for fingerprint image acquisition, coupled with the availability of more processing power on affordable computing systems, have generated significant interest in using fingerprints for several civil applications including authentication. In an automatic fingerprint identification system, it is desirable to estimate the image quality of the fingerprint image before it is processed for feature extraction. This helps in deciding on the type of image enhancements that are needed and in deciding on thresholds for the matcher in the case that dynamic thresholds are used. Several techniques for fingerprint image quality estimation in the spatial domain are described in the literature. In this paper, we propose a method for image quality estimation from a wavelet compressed fingerprint image. The results are compared with an existing model of quality estimation in the spatial domain. Our analysis shows that the results are very accurate estimations of the image quality. It further has the advantage that the image need not be fully decompressed if the quality measure does not exceed the threshold for acceptable image quality.