Open Access

ARTICLE

Automated Angle Detection for Industrial Production Lines Using Combined Image Processing Techniques

by Pawat Chunhachatrachai^1,*, Chyi-Yeu Lin^1,2

1 Department of Mechanical Engineering, National Taiwan University of Science and Technology, Taipei, 106, Taiwan
2 Center for Intelligent Manufacturing Innovation, National Taiwan University of Science and Technology, Taipei, 106, Taiwan

* Corresponding Author: Pawat Chunhachatrachai. Email:

Intelligent Automation & Soft Computing 2024, 39(4), 599-618. https://doi.org/10.32604/iasc.2024.055385

Received 25 June 2024; Accepted 24 July 2024; Issue published 06 September 2024

Abstract

Angle detection is a crucial aspect of industrial automation, ensuring precise alignment and orientation of components in manufacturing processes. Despite the widespread application of computer vision in industrial settings, angle detection remains an underexplored domain, with limited integration into production lines. This paper addresses the need for automated angle detection in industrial environments by presenting a methodology that eliminates training time and higher computation cost on Graphics Processing Unit (GPU) from machine learning in computer vision (e.g., Convolutional Neural Networks (CNN)). Our approach leverages advanced image processing techniques and a strategic combination of algorithms, including contour selection, circle regression, polar warp transformation, and outlier detection, to provide an adaptive solution for angle detection. By configuring the algorithm with a diverse dataset and evaluating its performance across various objects, we demonstrate its efficacy in achieving reliable results, with an average error of only 0.5 degrees. Notably, this error margin is 3.274 times lower than the acceptable threshold. Our study highlights the importance of accurate angle detection in industrial settings and showcases the reliability of our algorithm in accurately determining angles, thus contributing to improved manufacturing processes.

---

Keywords

---