Fingerprint Matching Using Feature Space Correlation

We present a novel fingerprint alignment and matching scheme that utilizes ridge feature maps to represent, align and match fingerprint images. The technique described here obviates the need for extracting minutiae points or the core point to either align or match fingerprint images. The proposed scheme examines the ridge strength (in local neighborhoods of the fingerprint image) at various orientations, using a set of 8 Gabor filters, whose spatial frequencies correspond to the average inter-ridge spacing in fingerprints. A standard deviation map corresponding to the variation in local pixel intensities in each of the 8 filtered images, is generated. The standard deviation map is sampled at regular intervals in both the horizontal and vertical directions, to construct the ridge feature map. The ridge feature map provides a compact fixed-length representation for a fingerprint image. When a query print is presented to the system, the standard deviation map of the query image and the ridge feature map of the template are correlated, in order to determine the translation offsets necessary to align them. Based on the translation offsets, a matching score is generated by computing the Euclidean distance between the aligned feature maps. Feature extraction and matching takes ~ 1 second in a Pentium III, 800 MHz processor. Combining the matching score generated by the proposed technique with that obtained from a minutiae-based matcher results in an overall improvement in performance of a fingerprint matching system.