Approximation model for fingerprint orientation field correction
The estimation of ?ngerprint Orientation Field (OF) plays an important role in most ?ngerprint feature extraction algorithms. Many of the later stages in ?ngerprint feature extraction process (e.g. ridge enhancement, singular points de-tection) utilize ?ngerprint OF information as a cornerstone, thus the far-reaching implication of its estimation to the whole recognition process. Unfortunately, the accurate and robust estimation of ?ngerprint OF in low-quality ?ngerprint images is di?cult and still remains as a challenge until today. This research attempts to evaluate the e?ectiveness of the ?ngerprint OF correction approaches based on the use of an approximation model derived from regression analysis. From the experimental results, it can be seen that performance of the approximation model based on Fourier basis is comparable to the classical ?lter-based approach to re- ?ne ?ngerprint OF. For practical purpose, a minor workaround can be utilized to signi?cantly enhance the performance of a Fourier series model. For the advance- ment of research on related ?elds, the author recommends a further exploration to search for a mathematical model which can better interpolate and extrapolate ?ngerprint?s ridge structure.
No other version available