DocumentCode :
475626
Title :
Constrained 2D Sketch Generation Based on Image Contour Detect
Author :
Ying, Shen ; Zhiyang, Chen ; Zhiyong, Cai
Author_Institution :
Comput. Sci. Coll., Zhejiang Univ., Hangzhou
Volume :
1
fYear :
2008
fDate :
3-4 Aug. 2008
Firstpage :
295
Lastpage :
298
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.
Keywords :
Hough transforms; curve fitting; edge detection; feature extraction; image colour analysis; randomised algorithms; 2D sketch generation; Hough transform; OTSU method; auto-extract contour sketch; binary image; circular arcs; color image; image contour detect; randomized circle detection algorithm; Background noise; Color; Constraint optimization; Curve fitting; Educational institutions; Image generation; Image recognition; Image segmentation; Product design; Spline; Constrained fitting; Contour tracking; Hough transform; Sketch constrain;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computing, Communication, Control, and Management, 2008. CCCM '08. ISECS International Colloquium on
Conference_Location :
Guangzhou
Print_ISBN :
978-0-7695-3290-5
Type :
conf
DOI :
10.1109/CCCM.2008.306
Filename :
4609518
Link To Document :
بازگشت