Recognition of character information for automation of production processes

Abstract

Purpose of research. Nowadays optical character recognition systems have a high level of dependence on the specific type of marking that is to be recognized, and therefore, the creation of a universal solution is an important and difficult task. The paper considers the issue of creating a system for recognizing symbolic information that can be used at various stages of production to automate processes in control systems, in particular, to analyze the labeling of circuit breakers.Methods. Binarization, filtering, and boundary detection are digital image processing techniques. Line search method, baseline search method, word splitting algorithms, image enhancement methods by segmentation, damaged characters recognition method, an algorithm for increasing the final recognition quality are character recognition methods.Results. The analysis of algorithms used for preprocessing and subsequent recognition of images containing marking of circuit breakers is carried out. The mathematical model of image processing for subsequent recognition has been created. We have described methods used to define marking symbols. Illustrative examples of the operation of the algorithms on which the system is built are given. The obtained solution was tested. The ways of system development are described here, they can lead to improved results, for particular use cases.Conclusion. It is proposed a solution that recognizes symbolic information on the labeling of circuit breakers, which can be the basis for the development and description of systems serving for the automation of production, by transferring information read from the product during the production process. This system, by its example, describes the components of character recognition systems, and for direct use, it needs to be refined in accordance with the technical requirements and the specifics of the conditions in which it will be used.