Computer Vision and Image Understanding

Special Issue on

Graph-Based representations

Guest Editors:
Edwin Hancock University of York, UK (
Andrea Torsello University of Venice, Italy (
Francisco Escolano University of Alicante, Spain (
Luc Brun ENSICAEN, France (

Notes: The submission deadline has been extended to November 30, 2009

Call for Papers

Graph-based representations are of pivotal importance in computer vision, pattern recognition and machine learning. They arise when the objects to be identified are decomposed into parts and relationships between them. Such representations are quite natural and find applications in low level image processing, such as segmentation or image filtering, and in high level vision tasks such as pattern matching. Graph representations also pose unique problems in machine learning, since they are non-vectorial in nature and require new methodology to be developed if they are to be learned from image data.

More generally, the strong and growing interest about graph based algorithms may be explained as follows: Todays pattern recognition tasks are less and less concerned with the analysis of a single image. Images are rather grouped in sequences (video) or in huge databases eventually disseminated over the Internet. This complex background for image analysis involves the use of many image features and the analysis of their relationships, which is typically a graph problem. Further, traditional feature-based approaches cannot satisfactorily deal with data that is naturally divided into part (e.g., shape or text analysis) or where contextual information is essential for the classification process. For these reasons the design of efficient graph-based algorithms for pattern recognition will certainly be one of the major challenge of the next decade.

The goal of this special issue is to solicit and publish high-quality papers that proivde a clear picture of the state of the art of the use of graphs as a representational tool in computer vision and pattern recognition. We aim to appeal to researchers in computer vision who are making non-trivial use of graph algorithms and their underlying theory, and also to interest theoretical computer scientists in the graph problems that arise in vision. Papers are solicited that address theoretical as well as practical issues related to the Special Issue's theme. Topics of interest include (but are not limited to):

  • Graph matching;
  • Graph-based image segmentation;
  • Irregular (graph) pyramids;
  • Graph representation of shapes;
  • Graph based learning;
  • Graph learning and clustering;
  • Graphs vs rigid structures (quadtrees, pyramids);
  • Graph transformations;
  • Data mining with graphs;
  • Graphs in constellation models;
  • Graphs in computational chemistry and bioinformatics;


Only electronic submissions will be accepted. submissions must go through the Elsevier Editorial System™.

The manuscripts must be submitted by November 30, 2009, and should conform to the standard guidelines of the Computer Vision and Image Understanding journal.

All submitted papers will be reviewed by at least three independent reviewers.