Abstract
The automatic recognition of welding targets is one of important automated tasks in robotic welding systems. Recognition feasibility depends strongly on feature extraction from welding target images captured by visual sensors. Because of its robustness in the face of image brightness perturbation and its invariance during the translation, transposition and mirroring of the target image, the singular value decomposition(SVD) of image matrix has been widely applied in many vision-based recognizing systems for feature extraction from target images. Unfortunately, target rotation causes the changes of the singular value that obstruct the application of SVD. A normalized SVD is presented here, in which the SVD of the target image is made along its major axis (minimum inertia axis), in order to keep the SVD invariant when the rotation of the target occurs. In the paper the singular values of a planar weldment using different viewing angles and using direct SVD and normalized SVD (along the major axis) are contrasted. In addition, the effect of the brightness of the target image on SVD is also presented. The experimental results show that the singular values obtained by the proposed method are invariant to the translation, rotation and scaling of the target image and can be applied to the automatic recognition of welding targets.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
