Analysis of shape recognition capability of Krawtchouk moments

In this paper, Krawtchouk invariant moments are used as features for object recognition. For hand images, the performance of Krawtchouk moments in terms of recognition accuracy, rotational invariance, scale invariance, computational time and feature vector size, has been analysed. A user independent dataset for 21 subjects under varying illumination conditions is created. A comparative analysis with Zernike moments is also done. Results confirm that Krawtchouk moments have a better shape recognition capability even for a very small feature set.