Rotation-invariant template matching based on ring projection and orientation codes

A fast rotation-invariant template matching method based on Ring Projection Transform(RPT) and Orientation Codes(OC) is proposed. The method consists of two stages. In the first stage, a ring projection method is applied to convert 2D image patches into ID vectors, based on which a rotation-invarian...

Full description

Saved in:
Bibliographic Details
Published inFifth International Conference on Intelligent Control and Information Processing pp. 192 - 197
Main Authors Bohong Wei, Fan Wang, Xiaopeng Hu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2014
Subjects
Accuracy
Algorithm design and analysis
Brightness
Correlation
Histograms
Noise
Vectors
Online AccessGet full text
ISBN1479936499
9781479936496
DOI10.1109/ICICIP.2014.7010338

Cover

More Information
Summary:A fast rotation-invariant template matching method based on Ring Projection Transform(RPT) and Orientation Codes(OC) is proposed. The method consists of two stages. In the first stage, a ring projection method is applied to convert 2D image patches into ID vectors, based on which a rotation-invariant similarity measure is designed. In the second stage, a template matching process based on OC is performed on a limited number of candidates selected by applying the similarity measure, leading to the high computational efficiency. The experimental results indicate that the matching accuracy of the proposed algorithm is superior to RPT and OC method.
ISBN:1479936499
9781479936496
DOI:10.1109/ICICIP.2014.7010338