Implementation of a system for classifying moving parts by color

Abstract

The purpose of this study is the development and implementation of a computer vision system for color identification in a set of parts, which were disposed on a continuously moving conveyor belt. The process for acquiring the images associated with the parts at issue, the preprocessing and treatment phases performed, as well as the results of the recognition of the feature of interest in each of these are exposed. It is worthy to mention that the feature of interest in the analyzed parts was established from three classes different, associated with the primary colors. The results obtained suggest the effectiveness of the implemented vision system, even as a prototype; which was integrated using low-cost and easy-to-use materials, and whose programming was developed in the open-source software Python, using the OpenCV library. Not only an effective recognition of the class corresponding to each part entered is highlighted, but also the possibility that said operation be executed without the conveyor belt used stopping its moving.