%0 Conference Proceedings
%4 sid.inpe.br/banon/2002/10.24.11.31
%2 sid.inpe.br/banon/2002/10.24.11.31.09
%@doi 10.1109/SIBGRA.2002.1167137
%T IFT-Watershed from gray-scale marker
%D 2002
%A Lotufo, Roberto,
%A Falcão, Alexandre Xavier,
%A Zampirolli, Francisco,
%E Gonçalves, Luiz Marcos Garcia,
%E Musse, Soraia Raupp,
%E Comba, João Luiz Dihl,
%E Giraldi, Gilson,
%E Dreux, Marcelo,
%B Brazilian Symposium on Computer Graphics and Image Processing, 15 (SIBGRAPI)
%C Fortaleza, CE, Brazil
%8 10-10 Oct. 2002
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%1 SBC - Brazilian Computer Society
%X The watershed transform and the morphological reconstruction are two of the most important operators for image segmentation in the framework of mathematical morphology. In many situations, the segmentation requires the classical watershed transform of a reconstructed image. In this paper, we introduce the IFT-watershed from gray scale marker - a method to compute at same time, the reconstruction and the classical watershed transform of the reconstructed image, without explicit computation of any regional minima. The method is based on the Image Foresting Transform (IFT) - a unified and efficient approach to reduce image processing problems to a minimum-cost path forest problem in a graph. As additional contributions, we demonstrate that (i) the cost map of the IFT-watershed from markers is identical to the output of the superior gray scale reconstruction; (ii) other reconstruction algorithms are not watersheds; and (iii) the proposed method achieves competitive advantages as compared to the current classical watershed approach.
%@language en
%3 93.pdf
%O The conference was held in Fortaleza, CE, Brazil, from October 7 to 10.