A filter bank method to construct rotationally invariant moments for pattern recognition

Authors:
Annupan Rodtook;Stanislav S. Makhanov
Affiliations:
Department of Computer Science, Ramkhamhaeng University, Bangkok 10240, Thailand;School of Information and Computer Technology, International Institute of Technology, Thammasat University, Bangkadi Campus, Pathumthani 12000, Thailand
Venue:
Pattern Recognition Letters
Year:
2007

Citing 9
Cited 0

On Image Analysis by the Methods of Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
Wavelets and dilation equations: a brief introduction

SIAM Review
Ten lectures on wavelets

Ten lectures on wavelets
Polynomial splines and wavelets: a signal processing perspective

Wavelets: a tutorial in theory and applications
Numerical experiments on the accuracy of rotation moments invariants

Image and Vision Computing
Fuzzy clustering with partial supervision

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Entropy-based algorithms for best basis selection

IEEE Transactions on Information Theory - Part 2
Image analysis by Tchebichef moments

IEEE Transactions on Image Processing
Image analysis by Krawtchouk moments

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.10

Visualization

Abstract

We propose multiresolution filter bank techniques to construct rotationally invariant moments. The multiresolution pyramid motivates a simple but efficient feature selection procedure based on a combination of a pruning algorithm, a new version of the Apriori mining techniques and the partially supervised fuzzy C-mean clustering. The recognition accuracy of the proposed techniques has been tested with the reference to conventional methods. The numerical experiments, with more than 50,000 images taken from standard image datasets, demonstrate an accuracy increase ranging from 5% to 27% depending on the noise level.