摘要：Fingerprint images are typically acquired using a contact-based sensor wherein a user places her finger on the surface of the sensor. The elastic nature of the human skin, coupled with the non-uniform pressure applied by the finger on the sensor, result in fingerprint images whose ridges exhibit non-linear distortions. For reliable matching, these non-linear distortion effects must be accounted for prior to comparing two fingerprint images. Models based on affine transformations have been used to offset the effects of distortion, but they invariably lead to unsatisfactory matching results since the distortions are basically elastic in nature.
