Image distortion correction algorithm based on lattice array coordinate projection

Xiao Luo*, Baoling Han, Qingsheng Luo, Xiaochuan Zhao

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

In order to improve the accuracy of image detection and target recognition, this paper presents an image distortion correction algorithm based on quadrilateral fractal approach controlling points. This method uses standard lattice image to be the measuring target, determines the coordinate by combining mathematical morphology and sliding neighborhood operation, and then Adopt simple linear regression analysis for optical center and establish coordinate system, finally proposes Two-step and one-dimensional gray linear interpolation backward mapping algorithm to define the pixel intensity. An image acquisition hardware system is designed contains TMS320DM6437 and taking a building as target. Experiments with above method have shown that this algorithm can correct distortion in short time without loss edge information.

Original languageEnglish
Title of host publicationICACTE 2010 - 2010 3rd International Conference on Advanced Computer Theory and Engineering, Proceedings
PagesV222-V226
DOIs
Publication statusPublished - 2010
Event2010 3rd International Conference on Advanced Computer Theory and Engineering, ICACTE 2010 - Chengdu, China
Duration: 20 Aug 201022 Aug 2010

Publication series

NameICACTE 2010 - 2010 3rd International Conference on Advanced Computer Theory and Engineering, Proceedings
Volume2

Conference

Conference2010 3rd International Conference on Advanced Computer Theory and Engineering, ICACTE 2010
Country/TerritoryChina
CityChengdu
Period20/08/1022/08/10

Keywords

  • Correction
  • Image distortion
  • Machine vision

Fingerprint

Dive into the research topics of 'Image distortion correction algorithm based on lattice array coordinate projection'. Together they form a unique fingerprint.

Cite this