Matching and normalization of affine deformed image from regular moments

Authors:
Jin Liu;Tianxu Zhang
Affiliations:
Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan 430074, PR China;Key Laboratory of Ministry of Education for Image Processing and Intelligent Control, Huazhong University of Science and Technology, Wuhan 430074, PR China
Venue:
Pattern Recognition Letters
Year:
2004

Citing 11
Cited 1

3-D Moment Forms: Their Construction and Application to Object Identification and Positioning

IEEE Transactions on Pattern Analysis and Machine Intelligence
Invariant Image Recognition by Zernike Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
The revised Fundamental Theorem of Moment Invariants

IEEE Transactions on Pattern Analysis and Machine Intelligence
Simple and fast computation of moments

Pattern Recognition
Fast computation of moment invariants

Pattern Recognition
The Method of Normalization to Determine Invariants

IEEE Transactions on Pattern Analysis and Machine Intelligence
Generalized Affine Invariant Image Normalization

IEEE Transactions on Pattern Analysis and Machine Intelligence
Degraded Image Analysis: An Invariant Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pictorial Recognition of Objects Employing Affine Invariance in the Frequency Domain

IEEE Transactions on Pattern Analysis and Machine Intelligence
n-Dimensional Moment Invariants and Conceptual Mathematical Theory of Recognition n-Dimensional Solids

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cross-Weighted Moments and Affine Invariants for Image Registration and Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence

An automatic method for generating affine moment invariants

Pattern Recognition Letters

Quantified Score

Hi-index	0.11

Visualization

Abstract

The notion of linear moment vector is introduced as an efficient approach for matching and normalization of affine deformed image. Least square error technique is introduced to improve the robustness and accuracy of the matching. By normalizing the linear moment vectors, the affine deformed image can be normalized. Our approaches are based only on regular moments that can be obtained easily from the image without extracting any feature point. The techniques can be generalized to n-dimensional case. The experiment results show that the proposed method gives good performance.