Fingerprint segmentation is one of the most important preprocessing steps in an automatic fingerprint identification system (AFIS). It is used to separate a fingerprint area iforeground) from the image background. Accurate segmentation of a fingerprint will greatly reduce the computation time of the following processing steps, and discard many spurious minutiae. In this paper, a new segmentation algorithm is presented. Apart from its simplicity, it is characterized by being neither depend on empirical thresholds chosen by experts or a learned model trained by elements generated from manually segmented fingerprints. The algorithm uses the block range as a feature to achieve fingerprint segmentation. Then, some Morphological closing and opening operations are performed, to extract the foreground from the image.The performance of the proposed technique is checked by evaluating the classification error (Err). Experimental results have shown that when analyzing FVC2004, FVC2002, and FVC2000 databases using the proposed algorithm, the average classification error rates are much less than those obtained by other approaches. Several illustrative examples are given to verifY this conclusion.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.