%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/08.11.22.17
%2 sid.inpe.br/sibgrapi/2016/08.11.22.17.01
%T Aprendizado ativo para classificação do vigor de sementes de soja
%D 2016
%A Pereira, Douglas Felipe,
%A Bugatti, Pedro Henrique,
%A Saito, Priscila Tiemi Maeda,
%@affiliation Federal University of Technology (UTFPR)
%@affiliation Federal University of Technology (UTFPR)
%@affiliation Federal University of Technology (UTFPR), University of Campinas (UNICAMP)
%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 aprendizado ativo, análise de imagens, processamento de imagens, classificação, sementes de soja.
%X The task of providing a high quality grain (e.g. soybean) to the farmer is a key challenge of the agrobusiness field. To achieve such quality considering soybean seeds it is applied the so-called tetrazolium test. This test provides an acurate diagnosis of the damages found in the seed, such as lacerations caused by insects, mechanical damages or high rates of humidity. These damages cause a considerable quality reduction and directly impact in the seed vigor. Some traditional machine learning methods were applied to the context of seed crops, in order to automatic classify the seed vigor. However, the great majority of the researches use the traditional supervised learning paradigm. Thus, in this paper we proposed to exploit the active learning paradigm to perform the classification of the seed vigor, derived from the tetrazolium test.
%@language pt
%3 2016-sibgrapi-wip.pdf