Core-based fingerprint image classification

This paper presents a new fingerprint classification algorithm that uses only the information related to core points. The algorithm uses an efficient enhancing method of fingerprint image for high-quality directional image. The algorithm detects core point candidates roughly from the directional image and adjusts the location of each core candidate for more exact result. In core analysis, the near area of each core candidate is examined. False core points made by noise are eliminated and the type and the orientation of core point are extracted for the classification step. Using this information, classification is performed. The algorithm was tested on 6283 images and classification accuracy of 92.3% for the four classes (arch, left-loop, right-loop, whorl) is achieved.