%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/08.16.15.51
%2 sid.inpe.br/sibgrapi/2016/08.16.15.51.15
%T Improvements on human skin segmentation in digital images
%D 2016
%A Sousa e Santos, Anderson Carlos,
%A Pedrini, Hélio,
%@affiliation University of Campinas
%@affiliation University of Campinas
%E Aliaga, Daniel G.,
%E Davis, Larry S.,
%E Farias, Ricardo C.,
%E Fernandes, Leandro A. F.,
%E Gibson, Stuart J.,
%E Giraldi, Gilson A.,
%E Gois, João Paulo,
%E Maciel, Anderson,
%E Menotti, David,
%E Miranda, Paulo A. V.,
%E Musse, Soraia,
%E Namikawa, Laercio,
%E Pamplona, Mauricio,
%E Papa, João Paulo,
%E Santos, Jefersson dos,
%E Schwartz, William Robson,
%E Thomaz, Carlos E.,
%B Conference on Graphics, Patterns and Images, 29 (SIBGRAPI)
%C São José dos Campos, SP, Brazil
%8 4-7 Oct. 2016
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K segmentation, saliency, texture, skin detection.
%X Human skin segmentation has several applications in computer vision and pattern recognition fields, whose main purpose is to distinguish skin and non-skin regions. Despite the large number of available methods, accurate skin segmentation is still a challenging task. Three main contributions toward this need are presented in this work. The first is a self-contained method for adaptive skin segmentation that adjusts the color model to a particular image. The second is the combination of saliency detection with color skin segmentation, which performs a background removal to eliminate non-skin regions. The third is a texture-based improvement imployed to characterize non-skin regions and thus eliminates color ambiguity adding a second vote. Experimental results on public data sets demonstrate a significant improvement of the proposed methods for human skin segmentation over state-of-the-art approaches.
%@language en
%3 paper.pdf