In this paper, a model-based compression algorithm is proposed to compress the fingerprint image data. The proposed model is based on parallel lines with identical orientations, arbitrary widths, and similar gray-level values positioned on a rectangle with a constant gray-level value as the background. This algorithm is referred to as Parallel Stroked Multi Line (PSML). A compression algorithm is developed based on Adaptive Geometrical Wavelet which employs PSML to preserve the fingerprint structure and minutiae. The proposed PSML algorithm has significant advantages over Wedgelets Transform and JPEG2000 in terms of PSNR value, visual quality of the compressed images, and compression effect on Automatic Fingerprint Identification Systems (AFIS). On the U.are.U 400 database, the mean EER rate for uncompressed images is 4.54%, whereas at extreme compression rates, like 267:1, this value is 49.41% and 6.22% for JPEG2000 and PSML, respectively. The results show a significant improvement compared to the standard JPEG2000 algorithm.

Keywords