Slap Fingerprint Segmentation

This paper presents a novel approach in seg- menting multiple fingerprints from an image. Such an image is taken by a scanner capable of recording several fingers simultaneously. A combination of two-staged mean shift and ellipse-fitting algorithms as well as an elaborate sub- sequent set of rules is used to segment the single fingertip images. First, the mean shift which is a well-established feature-space analysis technique is used to identify the dif- ferent components of the fingers. Then the orientation and size of each component is determined by the application of a robust ellipse-fitting algorithm. Finally the rules locate the fingertips. Extensive experimental evaluations demonstrate the success of the approach.