%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/07.13.18.25
%2 sid.inpe.br/sibgrapi/2015/07.13.18.25.12
%T Segmentação de Células Cervicais Utilizando Level Set Binário-Hierárquico
%D 2015
%A Braga, Alan Magalhães,
%A Marques, Regis Cristiano Pinheiro,
%A Medeiros, Fátima Nelsizeuma Sombra,
%A Ushizima, Daniela Mayumi,
%@affiliation Instituto Federal do Ceará
%@affiliation Instituto Federal do Ceará
%@affiliation Universidade Federal do Ceará
%@affiliation Berkeley Institute for Data Science, University of California, Berkeley & Computational Research Division, Lawrence Berkeley National Lab
%E Rios, Ricardo Araujo,
%E Paiva, Afonso,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador, BA, Brazil
%8 26-29 Aug. 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K cervical cancer cell, clusters detection, level set, image segmentation.
%X This paper introduces a hierarchical approach based on a binary level set algorithm for cervical cell segmentation. The proposed program recursively segments a region into two new regions, starting from the whole image. In each step of the hierarchical process, we use a multiscale strategy to estimate the number of clusters of the current region. A new division is performed if two or more clusters are detected. The segmentation process automatically terminates when all regions cannot be divided further, according to the criteria imposed by the proposed method. Experiments performed on the Herlev dataset showed the effectiveness of the proposed hierarchical algorithm.
%@language pt
%3 segmentacao-de-celulas_camera_ready.pdf