Multicriteria Robust Fitting of Elliptical Primitives

• Published in: Journal of mathematical imaging and vision 2014, Vol.49 (2), p.492-509
• Main Authors: Muñoz-Pérez, J., de Cózar-Macías, O. D., Blázquez-Parra, E. B., Ladrón de Guevara-López, I.
• Format: Article
• Language: English
• Subjects: Algorithmics. Computability. Computer arithmetics; Applications of Mathematics; Applied sciences; Artificial intelligence; Computer Science; Computer science; control theory; systems; Exact sciences and technology; Image Processing and Computer Vision; Mathematical Methods in Physics; Pattern recognition. Digital image processing. Computational geometry; Signal,Image and Speech Processing; Theoretical computing
• ISSN: 0924-9907; 1573-7683
• DOI: 10.1007/s10851-013-0480-1

Geometric fitting is present in different fields of science, engineering and astronomy. In particular, ellipse shapes are some of the most commonly employed geometric features in digital image analysis and visual pattern recognition. Most geometric and algebraic methods are sensitive to noise and outlier points and so the results are not usually acceptable. In this paper, a robust geometric multicriteria method based on the mean absolute geometric error and the eccentricity to fit an ellipse to set of points is proposed. It is well known that the least mean absolute error criterion leads to robust estimations. The experimental results on different real and synthetic data have shown that the proposed algorithm is robust to outliers. Moreover, it allows us to identify outliers and remove them.