Articles producció científica> Enginyeria Informàtica i Matemàtiques

Active contours driven by local and global fitted image models for image segmentation robust to intensity inhomogeneity

  • Dades identificatives

    Identificador: PC:2726
    Autors:
    Akram, F.Garcia, M.A.Puig, D.
    Resum:
    This paper presents a region-based active contour method for the segmentation of intensity inhomogeneous images using an energy functional based on local and global fitted images. A square image fitted model is defined by using both local and global fitted differences. Moreover, local and global signed pressure force functions are introduced in the solution of the energy functional to stabilize the gradient descent flow. In the final gradient descent solution, the local fitted term helps extract regions with intensity inhomogeneity, whereas the global fitted term targets homogeneous regions. A Gaussian kernel is applied to regularize the contour at each step, which not only smoothes it but also avoids the computationally expensive re-initialization. Intensity inhomogeneous images contain undesired smooth intensity variations (bias field) that alter the results of intensity-based segmentation methods. The bias field is approximated with a Gaussian distribution and the bias of intensity inhomogeneous regions is corrected by dividing the original image by the approximated bias field. In this paper, a two-phase model is first derived and then extended to a fourphase model to segment brain magnetic resonance (MR) images into the desired regions of interest. Experimental results with both synthetic and real brain MR images are used for a quantitative and qualitative comparison with state-of-the-art active contour methods to show the advantages of the proposed segmentation technique in practical terms.
  • Altres:

    Autor segons l'article: Akram, F.; Garcia, M.A.; Puig, D.
    Departament: Enginyeria Informàtica i Matemàtiques
    Autor/s de la URV: AKRAM, FARHAN; Garcia, M.A.; PUIG VALLS, DOMÈNEC SAVI
    Paraules clau: brain experimental model image segmentation
    Resum: This paper presents a region-based active contour method for the segmentation of intensity inhomogeneous images using an energy functional based on local and global fitted images. A square image fitted model is defined by using both local and global fitted differences. Moreover, local and global signed pressure force functions are introduced in the solution of the energy functional to stabilize the gradient descent flow. In the final gradient descent solution, the local fitted term helps extract regions with intensity inhomogeneity, whereas the global fitted term targets homogeneous regions. A Gaussian kernel is applied to regularize the contour at each step, which not only smoothes it but also avoids the computationally expensive re-initialization. Intensity inhomogeneous images contain undesired smooth intensity variations (bias field) that alter the results of intensity-based segmentation methods. The bias field is approximated with a Gaussian distribution and the bias of intensity inhomogeneous regions is corrected by dividing the original image by the approximated bias field. In this paper, a two-phase model is first derived and then extended to a fourphase model to segment brain magnetic resonance (MR) images into the desired regions of interest. Experimental results with both synthetic and real brain MR images are used for a quantitative and qualitative comparison with state-of-the-art active contour methods to show the advantages of the proposed segmentation technique in practical terms.
    Grup de recerca: Robòtica i Visió Intel.ligents
    Àrees temàtiques: Enginyeria informàtica Ingeniería informática Computer engineering
    Accès a la llicència d'ús: https://creativecommons.org/licenses/by/3.0/es/
    ISSN: 1932-6203
    Identificador de l'autor: ; ;
    Data d'alta del registre: 2017-04-26
    Volum de revista: 12
    Versió de l'article dipositat: info:eu-repo/semantics/publishedVersion
    Enllaç font original: http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174813
    URL Document de llicència: https://repositori.urv.cat/ca/proteccio-de-dades/
    DOI de l'article: 10.1371/journal.pone.0174813
    Entitat: Universitat Rovira i Virgili
    Any de publicació de la revista: 2017
    Pàgina inicial: Art.num. e0174813
    Tipus de publicació: Article Artículo Article
  • Paraules clau:

    Cervell
    Visió
    Robòtica
    brain
    experimental model
    image segmentation
    Enginyeria informàtica
    Ingeniería informática
    Computer engineering
    1932-6203
  • Documents:

  • Cerca a google

    Search to google scholar