Article: Postmatch pruning of SIFT pairs for iris recognition Journal: International Journal of Biometrics (IJBM) 2013 Vol.5 No.2 pp.160 - 180 Abstract: This article looks into pros and cons of the conventional global and local feature matching techniques for iris. The review of related research works on matching techniques leads to the observation that local features like scale invariant feature transform (SIFT) gives satisfactory recognition accuracy for good quality images. However the performance degrades when the images are occluded or taken non-cooperatively. As SIFT matches keypoints on the basis of 128-D local descriptors, hence it sometimes falsely pairs two keypoints which are from different portions of two iris images. Subsequently the need for filtering or pruning of faulty SIFT pairs is felt. The paper proposes two methods of filtering impairments (faulty pairs) based on the knowledge of spatial information of the keypoints. The two proposed pruning algorithms (angular filtering and scale filtering) are applied separately and applied in union to have a complete comparative analysis of the result of matching. The pruning approaches has given better recognition accuracy than conventional SIFT when experimented on two publicly available BATH and CASIAv3 iris databases. Inderscience Publishers - linking academia, business and industry through research

Title: Postmatch pruning of SIFT pairs for iris recognition

Authors: Sambit Bakshi; Hunny Mehrotra; Banshidhar Majhi

Addresses: Department of Computer Science and Engineering, National Institute of Technology Rourkela, Rourkela – 769008, Odisha, India ' Department of Computer Science and Engineering, National Institute of Technology Rourkela, Rourkela – 769008, Odisha, India ' Department of Computer Science and Engineering, National Institute of Technology Rourkela, Rourkela – 769008, Odisha, India

Abstract: This article looks into pros and cons of the conventional global and local feature matching techniques for iris. The review of related research works on matching techniques leads to the observation that local features like scale invariant feature transform (SIFT) gives satisfactory recognition accuracy for good quality images. However the performance degrades when the images are occluded or taken non-cooperatively. As SIFT matches keypoints on the basis of 128-D local descriptors, hence it sometimes falsely pairs two keypoints which are from different portions of two iris images. Subsequently the need for filtering or pruning of faulty SIFT pairs is felt. The paper proposes two methods of filtering impairments (faulty pairs) based on the knowledge of spatial information of the keypoints. The two proposed pruning algorithms (angular filtering and scale filtering) are applied separately and applied in union to have a complete comparative analysis of the result of matching. The pruning approaches has given better recognition accuracy than conventional SIFT when experimented on two publicly available BATH and CASIAv3 iris databases.

Keywords: scale invariant feature transform; SIFT; local feature matching; iris matching; pruning impairments; biometrics; iris recognition; iris images; image matching; image analysis; filtering impairments; recognition accuracy.

DOI: 10.1504/IJBM.2013.052965

International Journal of Biometrics, 2013 Vol.5 No.2, pp.160 - 180

Received: 08 May 2012
Accepted: 29 Aug 2012
Published online: 28 Feb 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Postmatch pruning of SIFT pairs for iris recognition

Keep up-to-date