Stereo matching algorithm of workpiece images based on improved shape context

FAN Ying; BAI Ruilin; WANG Xiuping; LI Xin

doi:10.7510/jgjs.issn.1001-3806.2016.06.009

In traditional shape context, the calculation complexity was high in traversing the contour sampling points to calculate the histogram similarity and it can not meet the industrial real-time requirements. In order to solve the problem, a fast stereo matching algorithm of workpiece images based on the improved shape context was proposed. In the disparity constraints of stereo image centroid, by using the histogram distribution of shape context, candidate matching points set were obtained and the calculation complexity was greatly reduced. To increase the discrimination between the matching points and non-matching points, the similarity measurement of shape context was weighted by the weighted coefficient. During the matching period, the improved shape context was combined with the histograms of oriented gradients of the corresponding contour feature points in 33 neighborhood to acquire the initial matching point set. At last, the false matching points were eliminated by random sample consensus algorithm. Theoretical analysis and experimental verification were applied to workpiece images, and the corresponding experimental comparison was presented. The experiment results show that this improved algorithm has higher precision, faster matching speed and high robustness.

Stereo matching algorithm of workpiece images based on improved shape context

Corresponding author: BAI Ruilin, bairuilin@hotmail.com;

1. Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education), Jiangnan University, Wuxi 214122, China;

2. Xinje Electronic Co. Ltd, Wuxi 214072, China

Received Date: 2015-10-14

Accepted Date: 2015-10-29

Available Online: 2016-11-25

Abstract: In traditional shape context, the calculation complexity was high in traversing the contour sampling points to calculate the histogram similarity and it can not meet the industrial real-time requirements. In order to solve the problem, a fast stereo matching algorithm of workpiece images based on the improved shape context was proposed. In the disparity constraints of stereo image centroid, by using the histogram distribution of shape context, candidate matching points set were obtained and the calculation complexity was greatly reduced. To increase the discrimination between the matching points and non-matching points, the similarity measurement of shape context was weighted by the weighted coefficient. During the matching period, the improved shape context was combined with the histograms of oriented gradients of the corresponding contour feature points in 33 neighborhood to acquire the initial matching point set. At last, the false matching points were eliminated by random sample consensus algorithm. Theoretical analysis and experimental verification were applied to workpiece images, and the corresponding experimental comparison was presented. The experiment results show that this improved algorithm has higher precision, faster matching speed and high robustness.

HTML

Reference (15)

[1]	ZHANG X P, WANG J Q, ZHANG Y X, et al. Large-scale three-dimensional stereo vision geometric measurement system[J]. Acta Optica Sinica, 2012, 32(3):140-147(in Chinese).
[2]	OH J K, LEE S, LEE C H. Stereo vision based automation for a bin-picking solution[J]. International Journal of Control, Automation, and Systems, 2012, 10(2):362-373.
[3]	SCHAUWECKER K, KLETTE R, ZELL A. A new feature detector and stereo matching method for accurate high-performance sparse stereo matching[C]//Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference. New York, USA:IEEE, 2012:5171-5176.
[4]	ZHU Y H, LI J Sh, YANG W, et al. A feature points description and matching algorithm for edge in IR/visual images[J]. Journal of Computer-Aided Design Computer Graphics, 2013, 25(6):857-864(in Chinese).
[5]	WANG J, FU J, LU H. Finding logos in real-world images with point-context representation-based region search[J]. Multimedia Systems, 2015, 21(3):301-311.
[6]	YU Y, HUANG K, CHEN W, et al. A novel algorithm for view and illumination invariant image matching[J].IEEE Transactions on Image Processing, 2012, 21(1):229-240.
[7]	ZHOU Y, LIU J T, BAI X. Research and perspective on shape matching[J]. Acta Automatica Sinica, 2012, 38(6):889-910(in Ch-inese).
[8]	LEORDEANU M, HEBERT M. A spectral technique for correspondence problems using pairwise constraints[C]//IEEE International Conference on Computer Vision. New York, USA:IEEE,2005:1482-1489.
[9]	ROMAN-RANGEL E, PALLAN C, ODOBEZ J M, et al. Analyzing ancient Maya glyph collections with contextual shape descriptors[J]. International Journal of Computer Vision, 2011, 94(1):101-117.
[10]	HU R X, JIA W, ZHANG D, et al. Hand shape recognition based on coherent distance shape contexts[J]. Pattern Recognition, 2012, 45(9):3348-3359.
[11]	HUANG W G, GU Ch, ZHU Zh K. PCA-SC shape matching for object recognition[J]. Optics and Precision Engineering, 2013, 21(8):2103-2110(in Chinese).
[12]	ZHENG D Ch, HAN M. Shape context based on H-EMD algorithm for shape matching[J]. Control and Decision, 2012, 27(11):1639-1643(in Chinese).
[13]	ZHENG D Ch, HAN M. Improved shape recognition method based on representative shape context[J]. Journal of Computer-Aided Design Computer Graphics, 2013, 25(2):215-220(in Chinese).
[14]	WU X Y, HE Y, YANG L, et al. Binary image retrieval based on improved shape context algorithm[J]. Optics and Precision Engineering, 2015, 23(1):302-309(in Chinese).
[15]	ZHOU E M, XUE F Zh, LI N. A fast edge detection algorithm on simple background[J]. Micro Computer Information, 2012, 10(10):383-384(in Chinese).

Stereo matching algorithm of workpiece images based on improved shape context

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views