Implementation of Workpiece Recognition and Location Based on Opencv

A method of workpiece recognition and location by Hu moment invariants based on Open Source Computer Vision(Opencv) is presented in this paper. Firstly, the methods of image preprocessing including image graying, mean filter, image binaryzation by adaptive threshold segmentation are used. Then, we extract the contours from the binary image. Finally, we can identify the object workpiece by matching the extracted contours with the object contour from the template image by Hu moment invariants. At the same time, the method of confirming the workpiece position and direction is put forward. Experimental results show that the proposed method can recognize the target workpiece and locate the position effectively. The used algorithms are simple and fast in operation.