A Fast template matching algorithm based on central moments of images

Ru Lai*, Xiangdong Liu, Fujio Ohkawa

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Citations (Scopus)

Abstract

This paper presents a new template matching algorithm in which the central moments are used as the matching features and the idea of integral image are used to decrease the time for image matching process. The algorithm also combines coarse-fine two-stage searching methods to effectively solve the problem of finding the peak point of the correlation functions accurately and robustly. It is different with traditional methods in which pixels are used as matching features. Experiment results show that the image process procedure can be finished within 40ms, which is the rate of image signal send from TV camera for real time object tracking. The results has broad applications in the fields of real time moving object tracking, pattern recognition and the machine vision, etc.

Original languageEnglish
Title of host publicationProceedings of the 2008 IEEE International Conference on Information and Automation, ICIA 2008
Pages596-600
Number of pages5
DOIs
Publication statusPublished - 2008
Event2008 IEEE International Conference on Information and Automation, ICIA 2008 - Zhangjiajie, Hunan, China
Duration: 20 Jun 200823 Jun 2008

Publication series

NameProceedings of the 2008 IEEE International Conference on Information and Automation, ICIA 2008

Conference

Conference2008 IEEE International Conference on Information and Automation, ICIA 2008
Country/TerritoryChina
CityZhangjiajie, Hunan
Period20/06/0823/06/08

Fingerprint

Dive into the research topics of 'A Fast template matching algorithm based on central moments of images'. Together they form a unique fingerprint.

Cite this