Enhanced Accuracy Moment Invariants for Biometric Recognition and Cryptosystems

Authors:
Shan Suthaharan
Affiliations:
Department of Computer Science, University of North Carolina at Greensboro, Greensboro, USA 27402
Venue:
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Year:
2009

Citing 7
Cited 0

Affine moment invariants: a new tool for character recognition

Pattern Recognition Letters
Generation of moment invariants and their uses for character recognition

Pattern Recognition Letters
Complete Sets of Complex Zernike Moment Invariants and the Role of the Pseudoinvariants

IEEE Transactions on Pattern Analysis and Machine Intelligence
Handbook of Fingerprint Recognition

Handbook of Fingerprint Recognition
Projective Moment Invariants

IEEE Transactions on Pattern Analysis and Machine Intelligence
Biometric Based Cryptographic Key Generation from Faces

DICTA '07 Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications
A Novel Cryptosystem Based on Iris Key Generation

ICNC '08 Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 04

Quantified Score

Hi-index	0.00

Visualization

Abstract

Numerical accuracy of moment invariants is very important for reliable feature extraction in biometric recognition and cryptosystems. This paper presents a novel approach to derive accuracy enhanced moment invariants that are invariant under translation, rotation, scaling, pixel interpolation and image cropping. The proposed approach defines a cosine based central moment and adopts a windowing mechanism to enhance accuracy of moment invariants under translation, rotation, scaling, pixel interpolation and image cropping. It derives moment invariants by extending the knowledge used in Hu's and Maitra's approaches. Simulation results show that the proposed moment invariants highly accurate than Hu's and Maitra's moment invariants.