English version


Guillaume Damiand

oPage d'accueil

oRecherches

oPublications

oEnseignements

oEncadrement de Thèses

oCV

oCoordonnées

oLiens

Tiled Top-Down Pyramids and Segmentation of Large Histological Images

Goffe R., Brun L., Damiand G.
Proc. of 8th Workshop on Graph-Based Representation in Pattern Recognition (GBR)
Lecture Notes in Computer Science 6658, pages 255-264, May 2011, Münster, Germany

Links:  PDF  Hal  Link  

Abstract: Recent microscopic imaging systems such as whole slide scanners provide very large (up to 18GB) high resolution images. Such amounts of memory raise major issues that prevent usual image representation models from being used. Moreover, using such high resolution images, global image features, such as tissues, does not clearly appear at full resolution. Such images contain thus different hierarchical information at different resolutions. This paper presents the model of tiled top-down pyramids which provides a framework to handle such images. This model encodes a hierarchy of partitions of large images defined at different resolutions. We also propose a generic construction scheme of such pyramids whose validity is evaluated on an histological image application.

Keywords: Irregular pyramid; Topological model; Combinatorial map.

BibTex references

@InProceedings{GBD11,
      author = {Goffe, R. and Brun, L. and Damiand, G.},
      title = {Tiled Top-Down Pyramids and Segmentation of Large Histological Images},
      booktitle = {Proc. of 8th Workshop on Graph-Based Representation in Pattern Recognition (GBR)},
      series = {Lecture Notes in Computer Science},
      publisher = {Springer Berlin/Heidelberg},
      volume = {6658},
      pages = {255-264},
      month = {May},
      year = {2011},
      address = {M\ünster, Germany},
      keywords = {Irregular pyramid; Topological model; Combinatorial map.},
      url = {https://doi.org/10.1007/978-3-642-20844-7_26}
}

Image


o [Retour]