Manuscript received May 26, 2025; revised June 26, 2025; accepted July 28, 2025; published January 16, 2026.

Abstract—This paper presents the development of a visionbased automated positioning system for machining processes. To achieve accurate positioning and obtain geometric information of machined parts, the relationship between the image coordinate system and the world coordinate system was established through a coordinate calibration process. In this study, a camera was mounted above the working platform to capture images of the machining area. Noise introduced by image subtraction was removed using thresholding operations, followed by edge detection methods to determine the contours of the machined parts. Wind deflectors were used as a case study. A quadratic transformation method was investigated and applied for coordinate calibration. In this process, when the camera resolutions in the OX and OY axes were 0.632 mm/pixel and 0.761 mm/pixel, respectively, the total positioning errors in the OX and OY axes were 1.108 mm and 1.271 mm, respectively. Experimental results demonstrate that the proposed system provides a robust and effective solution for positioning during the machining process.

Keywords—image processing, machine vision, positioning system, edge milling

Cite: Hsu Q. Cherng, Ngoc V. Ngo, and Kun M. Chen, "Vision-Based Automation Positioning System for Edge-Milling," Journal of Image and Graphics, Vol. 14, No. 1, pp. 15-23, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC-BY-4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.