Fingerprint Core Point Detection Based on SVM and Complex Filter
Core point is an essential feature of a fingerprint. Fingerprint core point detection is an important step for fingerprint matching and classification. This paper presents a two stages algorithm for fingerprint core point detection. First, local fingerprint style is used as the basis for constructing feature data, then SVM is use to localize fingerprint core point candidate regions. Second, a novel complex filter is designed according to the ridge trend around fingerprint core point, and accurate fingerprint core point detection is implemented by using the complex filter in candidate regions. Experimental results show that the proposed method can detect the position and orientation of fingerprint core point in a precise and fast way.