The key idea of proposed classification method in is dividing fingerprint into small sub-images using singular point location, and then, creating distinguished patterns for each class using frequency domain representation for each sub-image. Figure 1 shows the five most common classes of the Galt onâHenry classification scheme (arch, tented arch, left loop, right loop, and whorl): A fingerprint can be simply classified according to the number and positions of the singularities this is the approach commonly used by human experts for manual classification, therefore several authors proposed to adopt the same technique for automatic classification. A delta point is the center of triangular regions where three different direction flows meet. Henry defined the core point as "the north most point of the innermost ridge line". In fingerprint classification algorithms, extracting the number and precise locations of singular points (SP), namely core and delta points are very important. After that, input data needs to be matched only with same class images. Many fingerprint classification methods rely on ridge flow or global features. ![]() ![]() In huge databases, fingerprints are divided into some classes first, to reduce the search time and then matching phase took place. The use of fingerprints for criminal verification, forensics, access control, credit cards, driver license registration and passport authentication is becoming very popular. last decades, fingerprint recognition has received great attention because of its unique properties like easy acquisition, universality, permanency and circumvention.
0 Comments
Leave a Reply. |