Hierarchical classification-based region growing (HCBRG): a collaborative approach for object segmentation and classification

  • Authors:

  • Aymen Sellaouti;Atef Hamouda;Aline Deruyver;Cédric Wemmert

  • Affiliations:

  • Laboratory of Computing in Programming, Algorithmic and Heuristic (LIPAH), Faculty of Sciences of Tunis, Campus Universities Tunisia, Tunisia, Image Sciences, Computer Sciences and Remote Sensing ...;Laboratory of Computing in Programming, Algorithmic and Heuristic (LIPAH), Faculty of Sciences of Tunis, Campus Universities Tunisia, Tunisia;Image Sciences, Computer Sciences and Remote Sensing Laboratory (LSIIT), University of Strasbourg, France;Image Sciences, Computer Sciences and Remote Sensing Laboratory (LSIIT), University of Strasbourg, France

  • Venue:
  • ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part I
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Object-based image classification approaches heavily rely on the segmentation process. However, the lack of interaction between both segmentation and classification steps is one of the major limits of these approaches. In this paper, we introduce a hierarchical classification based on a region growing approach driven by expert knowledge represented in a concept hierarchy. In order to overcome the region growing's limits, a first classification will associate a confidence score to each region in the image. This score will be used through an iterative step, which allows interaction between segmentation and classification at each iteration. Carried out experiments on a Quickbird image show the benefits of the introduced approach.