• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail - Request a copy

A New Finsler Minimal Path Model with Curvature Penalization for Image Segmentation and Closed Contour Detection

Chen, Da; Mirebeau, Jean-Marie; Cohen, Laurent D. (2016), A New Finsler Minimal Path Model with Curvature Penalization for Image Segmentation and Closed Contour Detection, 2016 IEEE Conference on Computer Vision and Pattern Recognition, IEEE. 10.1109/CVPR.2016.45

Type
Communication / Conférence
Date
2016
Conference title
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference date
2016-06
Conference city
Las Vegas
Conference country
United States
Book title
2016 IEEE Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Publication identifier
10.1109/CVPR.2016.45
Metadata
Show full item record
Author(s)
Chen, Da
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Mirebeau, Jean-Marie
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Cohen, Laurent D.
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Abstract (EN)
In this paper, we propose a new curvature penalized minimal path model for image segmentation via closed contour detection based on the weighted Euler elastica curves, firstly introduced to the field of computer vision in [22]. Our image segmentation method extracts a collection of curvature penalized minimal geodesics, concatenated to form a closed contour, by connecting a set of user-specified points. Globally optimal minimal paths can be computed by solving an Eikonal equation. This first order PDE is traditionally regarded as unable to penalize curvature, which is related to the path acceleration in active contour models. We introduce here a new approach that enables finding a global minimum of the geodesic energy including a curvature term. We achieve this through the use of a novel Finsler metric adding to the image domain the orientation as an extra space dimension. This metric is non-Riemannian and asymmetric, defined on an orientation lifted space, incorporating the curvature penalty in the geodesic energy. Experiments show that the proposed Finsler minimal path model indeed outperforms state-of-the-art minimal path models in both synthetic and real images.
Subjects / Keywords
Measurement; Computational modeling; Mathematical model; Active contours; Image segmentation; Force; Feature extraction

Related items

Showing items related by title and author.

  • Thumbnail
    New Elastica Geodesic Approach with Convexity Shape Prior for Region-based Active Contours and Image Segmentation 
    Chen, Da; Mirebeau, Jean-Marie; Tai, Xue-Cheng; Cohen, Laurent D. (2021) Document de travail / Working paper
  • Thumbnail
    A Generalized Asymmetric Dual-front Model for Active Contours and Image Segmentation 
    Chen, Da; Spencer, Jack; Mirebeau, Jean-Marie; Chen, Ke; Shu, Minglei; Cohen, Laurent D. (2021) Article accepté pour publication ou publié
  • Thumbnail
    Global Minimum for a Finsler Elastica Minimal Path Approach 
    Chen, Da; Mirebeau, Jean-Marie; Cohen, Laurent D. (2016) Article accepté pour publication ou publié
  • Thumbnail
    Finsler Geodesic Evolution Model for Region based Active Contours 
    Chen, Da; Mirebeau, Jean-Marie; Cohen, Laurent D. (2016) Communication / Conférence
  • Thumbnail
    Global Minimum for Curvature Penalized Minimal Path Method 
    Chen, Da; Cohen, Laurent D.; Mirebeau, Jean-Marie (2015) Communication / Conférence
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo