Computer Vision and Graphics

Volume 7594 of the series Lecture Notes in Computer Science pp 475-482

Revisiting Component Tree Based Segmentation Using Meaningful Photometric Informations

  • Michał Kazimierz KowalczykAffiliated withLORIA, UMR 7503, Université de Lorraine
  • , Bertrand KerautretAffiliated withLORIA, UMR 7503, Université de Lorraine
  • , Benoît NaegelAffiliated withLSIIT, UMR 7005, Université de Strasbourg
  • , Jonathan WeberAffiliated withLORIA, UMR 7503, Université de Lorraine

* Final gross prices may vary according to local VAT.

Get Access


This paper proposes to revisit a recent interactive segmentation algorithm based on an original image representation called the component-tree [1]. This method relies on an optimisation process allowing to choose a segmentation result fitting at best some image markers defined by the user. We propose different solutions to improve the efficiency of the method, in particular by including meaningful photometric informations and by assessing automatically the user parameter α.