Skip to Main content Skip to Navigation

Etude des courbes discrètes : applications en analyse d'images

Abstract : In this thesis, we are interested in the study of discrete curves and its applications in image analysis. We have proposed an amelioration of curvature estimation based on circumcircle. This method is based on the notion of blurred segment of width [nu] and on the decomposition of a curve into the sequence of maximal blurred segment of width [nu]. Afterwards, we have applied this idea in 3D to estimate the discrete curvature and torsion at each point of a 3D curve. Concerning the applications, we have developed a rapid et reliable method to detect dominant points of a 2D curve. A dominant point is a point whose the curvature value is locally maximum. The dominant points play an important role in pattern recognition. Our method uses a parameter: the width of maximal blurred segments. Based on this novel method of dominant point detection, we proposed free-parameter methods for polygonal representation. They are based on a multi-width approach. Otherwise, we are interested in discrete arcs and circles. A linear method has been proposed for the recognition of arcs and circles. We then develop a new method for segmentation of noisy curves into arcs based on a method of noise detection. We also proposed a linear method to measure the circularity of closed curves. In addition, we have proposed a robust method to decompose a curve into arcs and line segments
Document type :
Complete list of metadata

Cited literature [121 references]  Display  Hide  Download
Contributor : Thèses UL Connect in order to contact the contributor
Submitted on : Thursday, March 29, 2018 - 10:32:26 AM
Last modification on : Saturday, October 16, 2021 - 11:26:08 AM
Long-term archiving on: : Thursday, September 13, 2018 - 1:09:47 PM


Files produced by the author(s)


  • HAL Id : tel-01746364, version 1



Thanh Phuong Nguyen. Etude des courbes discrètes : applications en analyse d'images. Autre [cs.OH]. Université Henri Poincaré - Nancy 1, 2010. Français. ⟨NNT : 2010NAN10095⟩. ⟨tel-01746364⟩



Record views


Files downloads