An efficient slap fingerprint segmentation and hand classification algorithm

This paper proposes an efficient algorithm to segment all fingertips from a slap-image and to identify them into their corresponding indices i.e. index, middle, ring or little finger of left/right hand. Geometrical and spatial properties have been used to identify these fingertips. The proposed algorithm can handle various challenges like the presence of dull prints, large rotational angles of the hand, small variation in the orientation of the fingertips and non-elliptical shape of components. It has been tested on a database of 6732 images of 1122 subjects. Experimental results reveal the segmentation of all fingertips from slap-images with an accuracy of 99.02%. (C) 2014 Elsevier B.V. All rights reserved.