In the Automatic Fingerprint Identification Syst e m (AFIS), extracting the feature of fingerprint is very important. The local cur vature of ridges of fingerprint is irregular, so people have the barrier to effe ctively extract the fingerprint curve features to describe fingerprint. This art icle proposes a novel algorithm; it embraces information of few nearby fingerpri nt ridges to extract a new characteristic which can describe the curvature featu re of fingerprint. Experimental results show the algorithm is feasible, and the characteristics extracted by it can clearly show the inner macroscopic curve pro perties of fingerprint. The result also shows that this kind of characteristic i s robust to noise and pollution.
展开▼
