Ellipse Detection via Global Arc Compatibilities and Adaptive Co-Clustering for Real-World Measurement Systems

Ellipse detection plays a crucial role in computer vision and measurement systems, yet existing methods often struggle with handling spatially distant arc segments, high computational complexity, and sensitivity to noise and complex geometries. In this paper, we propose a novel ellipse detection method that addresses these limitations through global arc compatibility analysis and adaptive co-clustering. We develop a probabilistic framework to represent ellipse distributions associated with detected arc segments, using Jensen-Shannon (JS) divergence to quantify arc compatibilities across the entire image. Moreover, we design an adaptive co-clustering algorithm based on Singular Value Decomposition (SVD) that efficiently groups compatible arcs while automatically estimating the number of ellipses present. This approach significantly improves detection accuracy in complex scenarios, as demonstrated by our experiments on synthetic and real-world datasets, including applications in industrial quality control and optical calibration systems. Compared to state-of-the-art methods, our algorithm achieves a 10% improvement in accuracy and 15% in recall on synthetic images, excelling particularly in detecting small and occluded ellipses. Our method provides a robust, efficient solution for ellipse detection, enhancing measurement precision across diverse imaging conditions.