%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/09.08.22.05
%2 sid.inpe.br/sibgrapi/2016/09.08.22.05.19
%T Realce de regiões em imagens de ultrassom de câncer mamário baseado em funções q -sigmóides
%D 2016
%A Massa, Paulo Gabriel,
%A Ribeiro, Monael Pinheiro,
%A Lopes, Guilherme Alberto Wachs,
%A Rodrigues, aulo Sergio Silva,
%@affiliation Centro de Matemática, Computação e Cognição da Universidade Federal do ABC, Santo André, Brasil
%@affiliation Centro de Matemática, Computação e Cognição da Universidade Federal do ABC, Santo André, Brasil
%@affiliation Departamento de Ciência Computação do Centro Universitário FEI, São Bernardo, Brasil
%@affiliation Departamento de Ciência Computação do Centro Universitário FEI, São Bernardo, Brasil
%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 contrast enhancement, sigmoid, tsallis statistics, ultra-sound images, q-exponential, q-sigmoid, q-gaussian.
%X AbstractThis paper introduces by the first timethe q-Sigmoid functions, a variation of the so called Sigmoid function, which is based on exponential kernels. This new function is based on non-extensive Tsallis statistics, through the use of q-Exponential kernels. The potential of this new function is demonstrated under the context of digital image processing, particularly for contrast enhancement and highlight regions of interest in ultrasound images of breast cancer. In the preliminary experiments, the proposed method showed good performance for both benign and malignant tumor images, significantly highlighting the region of interest from its background. This suggests that the proposed methodology can be explored in CAD (Computed AidedDiagnosis) systems as a pre-processing step of later stages such as segmentation and extraction of lesion contours before the shape and texture analysis stages in a system of automatic diagnosis.
%@language pt
%3 paper-qenhancement-ufabc.pdf