Mobile Phone Shell Detection and Location based on Direction Vector

In the electronic production line, due to the random placement of materials, their own shape irregularity and other factors, resulting in the realization of the target detection is much more difficult. In this paper, we take the mobile phone shell as the object of grasping, combined with the feature analysis of the mobile phone shell, we propose a mobile phone shell detection and position algorithm based on the direction vector. Firstly, noise reduction is performed on the image captured by the camera. Secondly, the edge information of the target in the image is selected as the direction vector for feature extraction, and finally, the template as well as the image to be tested are matched to produce the target detection results and rectangle fitting is used to locate the mobile phone shell. This paper compares the recognition effect of this algorithm with the traditional rectangular detection based mobile phone shell algorithm, and the algorithm was used to capture the mobile phone shell experiment for 100 times, and the number of successful captures was 95 times, the success rate is 95% with a high degree of accuracy.