A High-quality Ellipse Detection Method for Machine Vision Based on Geometric Constraints and Hierarchical Clustering

Abstract

In machine vision, elliptical targets frequently appear within the camera's region of interest (ROI). Ellipse detection is essential for shape detection and geometric measurements in machine vision. However, existing ellipse detection algorithms often face issues such as high computational complexity, strong dependence on initial conditions, sensitivity to noise, and lack of robustness to occlusions.In this paper, we propose a fast and robust ellipse detection method to address these challenges. This method first utilizes edge gradient and curvature information to segment the curve into circular arcs. Next, based on the convexity of the arcs, it divides them into different quadrants of the ellipse,groups and fits the arcs according to multiple geometric constraints at a low computational cost. Finally, it reduces the parameter space for hierarchical clustering and then segments the complete ellipse into several sectors for verification.We compare our method across seven datasets, including five public image datasets and two from industrial camera scenes. Experimental results show that our method achieves a precision ranging from 67.1% to 98.9%, a recall ranging from 48.1% to 92.9%, and an F-measure ranging from 58.0% to 95.8%. The average execution time per image ranges from 25 ms to 192 ms, demonstrating both high accuracy and efficiency.