A method of workpiece location based on improved generalized Hough transform

Abstract

Abstract In order to solve the problem that the workpiece is not easy to identify in the complex environment in the industrial processing, sorting and other automatic production links, a workpiece positioning method based on Improved Generalized Hough transform, also known as eif-ght, is proposed. In order to solve the problem of large time consumption and high memory consumption of traditional generalized Hough transform in target detection, this paper uses the rotation invariant feature angle formed by any two edge points in the image as the R table index under the condition of image preprocessing to realize the representation of target shape, and uses particle swarm intelligent evolutionary algorithm to speed up the search The final target is determined by similarity measurement. The experimental results show that when the workpiece rotates and shifts, and in the complex environment with noise, local occlusion, nonlinear illumination and so on, it can achieve stable and efficient positioning.