Fuzzy Modelling of Local Linearity in Contours Chamorro-Martínez, Jesús Martínez-Jiménez, Pedro Manuel Garrido, Antonio Soto-Hidalgo, José Manuel Image Analysis Fuzzy Modelling Local Linearity Contours This is the peer reviewed version of the following article: Jesús Chamorro-Martínez, Pedro Manuel Martínez-Jiménez, Antonio Garrido, José Manuel Soto-Hidalgo, “Fuzzy modelling of local linearity in contours” (2018), IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2018), Rio de Janeiro (Brasil), 8-13 Julio 2018. DOI: 10.1109/FUZZ-IEEE.2018.8491659 © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Shape analysis, and particulary the contour study, is a fundamental task for object recognition in images. In this paper, a fuzzy approach for representing the linearity property of a contour segment is proposed. Linearity is a key property related to which degree a contour segment is a curve or a straight line; in addition, it is the basis for modelling other properties like curvature, salience or concavity/convexity. In this framework, firstly, the idea of linearity vs non-linearity, and the meaning of its fulfilment, will be analyzed. Secondly, the definition of a membership function according to that meaning will be proposed on the basis of the coefficient of determination. Finally, we will show the goodness of our proposal by analyzing linearity in a set of shapes with different characteristics. 2024-02-10T11:06:22Z 2024-02-10T11:06:22Z 2018 info:eu-repo/semantics/conferenceObject https://hdl.handle.net/10481/88926 10.1109/FUZZ-IEEE.2018.8491659 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess Attribution-NonCommercial-NoDerivatives 4.0 Internacional