Constrained 2D sketch generation based on image contour detect

  • Shen Ying*
  • , Chen Zhiyang
  • , Cai Zhiyong
  • *Corresponding author for this work

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

Abstract

We proposed a method to auto-extract contour sketch from color image. Firstly, we get binary image through OTSU method, and then trace the contour of the binary image. Secondly, map the contour to the specified sketch plane. We use Hough Transform to detect all possible line segments in the contour, use Randomized Circle Detection algorithm to get all possible circular arcs, and then determine the break points of the contour according to the constraints between the fitted line segments and circular arcs. Finally, we refit the curve set by the global constraint formula based on the estimated curve type and constraints. Examples show that the method can recognize the curve type and corresponding constraints accurately, and can extract contour sketch from the color image as expected.

Original languageEnglish
Title of host publicationProceedings - ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM 2008
Pages295-298
Number of pages4
DOIs
Publication statusPublished - 2008
Externally publishedYes
EventISECS International Colloquium on Computing, Communication, Control, and Management, CCCM 2008 - Guangzhou, China
Duration: 3 Aug 20084 Aug 2008

Publication series

NameProceedings - ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM 2008
Volume1

Conference

ConferenceISECS International Colloquium on Computing, Communication, Control, and Management, CCCM 2008
Country/TerritoryChina
CityGuangzhou
Period3/08/084/08/08

Fingerprint

Dive into the research topics of 'Constrained 2D sketch generation based on image contour detect'. Together they form a unique fingerprint.

Cite this