Robust ellipse detection via duality principle with a false determination control

• Main Authors: Dong, Huixu, Chen, I-Ming, Prasad, Dilip Kumar
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Ellipse Detection; Principle of Geometric Duality
• Online Access: https://hdl.handle.net/10356/140450
• Institution: Nanyang Technological University

In this paper, we propose a novel ellipse detection approach that eliminates false detection-based parameter space decomposition, principal of symmetric tangents, and a novel geometric constraint utilizing properties of tangents of ellipses. The principle of symmetric tangents provides better computational efficiency through confirmation of the ellipse center in the decomposed parameter space. The geometric constraint is used for alleviating the false detection probability. The experimental results confirm that the approach detects ellipse with an excellent accuracy at a high speed.