Features Extraction for Structured Light Stripe Image Based on OTSU Threshold

Author

Zhang, Lei ; Xu, Yongkang ; Wu, Chuanyu

Author_Institution

Fac. of Mech. Eng. & Autom., Zhejiang Sci-Tech Univ., Hangzhou, China

fYear

2011

fDate

8-9 Oct. 2011

Firstpage

92

Lastpage

95

Abstract

Computer vision systems are playing an important role in 3D measurement for industrial applications. A method of image process and features extraction for structured light stripe image of Tailored Weld Blanks with arc and splash disturbance is proposed. Then, the target image is pre-processed using image median filtering and setting range of interest. Furthermore, several thresholds of Gray Centroid Algorithm are determined based on OSTU. Finally, a k-times gray center of mass average method is used to extract mid-line of sub-pixel laser stripe. Experimental results are shown and the validity of the proposed algorithm has been proved.

Keywords

computer vision; feature extraction; laser beam welding; measurement; median filters; production engineering computing; 3D measurement; Otsu threshold; arc disturbance; computer vision system; feature extraction; gray center-of-mass average method; gray centroid algorithm; image median filtering; industrial application; splash disturbance; structured light stripe image; tailored weld blank; Automation; Laser noise; Lasers; Robot kinematics; Service robots; Welding; OTSU; features extraction; image processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge Acquisition and Modeling (KAM), 2011 Fourth International Symposium on

Conference_Location

Sanya

Print_ISBN

978-1-4577-1788-8

Type

conf

DOI

10.1109/KAM.2011.32

Filename

6137586