Classification of fingerprint based on traced orientation flow

In this paper we present an innovative fingerprint classification scheme based on hierarchical singular point detection and traced orientation flow. A novel technique for histogram specification is devised to enhance the separation between ridge and valley for the captured fingerprint. Then we segment the Region of Interested (ROI) region by projection on eight specified angles to locate the boundary. Afterwards, the original image is transformed into the energy image and therefore the impression region for orientation estimation is relocated by refining ROI region through contour detection. Finally, the class label is assigned per the traced orientation flow and related threshold setting. The performance of the proposed method has been validated through experiments on the NIST4 database.