COMPUTER VISION FOR AUTONOMOUS VISUAL INSPECTION IN INDUSTRIAL PRODUCTION LINES

This article has the specific objectives of highlighting the computer vision techniques used in the IVAP project, discussing the stages of implementation of the system and analyzing the results obtained. Throughout this study, we hope to contribute to the existing literature on the application of computer vision in industry, citing examples from authors such as Gerald J. Agin (1980) and Rodrigo Barbosa Davies (2012), who explored the practice and effectiveness of these technologies in industrial settings. Computer vision has established itself as an essential tool for visual inspection in industrial production lines, promoting significant improvements in the quality and efficiency of manufacturing processes. This study addresses the implementation of an advanced computer vision system in the IVAP (Visual Autonomous Product Inspection) project, developed in partnership between the Conecthus Institute and Vantiva. The implementation of the Keyence CV-X Series system was motivated by the need to perform autonomous inspections, standardizing product quality without relying on manual evaluations, which are prone to errors. The development of the project focused on the use of sophisticated computer vision techniques, including defect detection and classification through machine learning algorithms for image processing and cosmetic defect analysis. The techniques used were studied and adapted to the industrial context, allowing the detailed inspection of cosmetic aspects of the products, with minimal exceptions. These techniques, which included lighting adjustments, camera sensitivity, and algorithms for detecting smudges and scratches, were crucial to the system's effectiveness.