TY  - EJOU
AU  - Chunhachatrachai, Pawat 
AU  - Lin, Chyi-Yeu 

TI  - Automated Angle Detection for Industrial Production Lines Using Combined Image Processing Techniques
T2  - Intelligent Automation \& Soft Computing

PY  - 2024
VL  - 39
IS  - 4
SN  - 2326-005X

AB  - 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.
KW  - Angle detection; image processing algorithm; computer vision; machine vision; industrial automation

DO  - 10.32604/iasc.2024.055385