A note on the least squares fitting of ellipses
Pattern Recognition Letters
Direct Least Square Fitting of Ellipses
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Data Mining, (First Edition)
Introduction to Data Mining, (First Edition)
Geometrical, Physical and Text/Symbol Analysis Based Approach of Traffic Sign Detection System
IEICE - Transactions on Information and Systems
Arc-based evaluation and detection of ellipses
Pattern Recognition
Direct type-specific conic fitting and eigenvalue bias correction
Image and Vision Computing
A hierarchical approach for fast and robust ellipse extraction
Pattern Recognition
Multiple ellipses detection in noisy environments: A hierarchical approach
Pattern Recognition
Splitting touching cells based on concave points and ellipse fitting
Pattern Recognition
A novel approach to video-based pupil tracking
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Edge curvature and convexity based ellipse detection method
Pattern Recognition
| Hi-index | 0.00 |
Least squares based ellipse detection is used as a core process in many image processing applications. In order to restrict the solution to ellipses and avoid non-elliptic conics, constrained optimization has to be incorporated in the least squares model. This paper proposes a least squares method that does not require a constrained optimization and has very low false positive rates. In contrast to the algebraic model of conics, we use the geometric model of ellipse and minimize the geometric distance of the fitted ellipse from the digital curve. As a result, the solutions are strictly restricted to ellipses. Results demonstrate a superior performance than most least squares based method for elliptic curves and greater true negative rates for non-elliptic curves even in presence of 30% noise.