Convergence region size research of television signal superposition iteration method for measurement machine vision system

Abstract

Background. Image processing is used in machine vision measurement systems, which are widely used in industrial applications. One of the important tasks in processing is image superposition. Registration methods must fulfill two basic requirements: satisfactory registration quality and practical processing time. One of the methods that meets these requirements is iterative superposition. Aim. The aim is to study the size of the area (region of convergence) for the values of the parameters of the initial approximation, which ensures satisfactory superposition. The size of the region determines the performance of the iterative algorithm. Methods. The size of the region of convergence was determined experimentally: correlation analysis and statistical simulation. Results. Experiments have shown if a sampling step is no more than 1/10 of the size of the image fragment, then the probability of correct registration is almost equal to one. If this threshold is exceeded, then the probability decreases. Conclusion. The size of the region of convergence of the iterative image registration method has been established. It is possible to design processing algorithms and predict processing time by obtaining results. The superposition method was introduced into a machine vision system to recognize contact wire clamps on the railway. Image superposition in this system is carried out in real time.