Parallel processing for Fingerprint feature extraction

Real time fingerprint identification based on original non-alphanumeric content matching shouldn´t compromise with its speed factor. Real production-quality implementation usually equipped with specific machine architecture to optimize this factor. On this research, we focus on achieving higher speed on common machine with respect to fingerprint accuracy factor. We explore the possibility to optimize execution time of fingerprint minutiae-based feature extraction using parallel process. Hypothetically, in general using parallel process will be faster than using sequential process. Taking advantage of multicore processor technology, optimization of execution time of fingerprint feature extraction is conducted using parallel process by processor cores. We have identified the possibility to implement parallel process on 29 different routines that are executed once or more. We compare result of average execution time of a fingerprint feature extraction using parallel and sequential process on Set B of Database 1 of Fingerprint Verification Contest 2000, 2002, and 2004. The experiment confirms the hypothesis and gives consistent result, i.e. faster about 57%, 55%, and 60% for each tested database.