%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/08.08.18.29
%2 sid.inpe.br/sibgrapi/2016/08.08.18.29.09
%T Interactive Segmentation of Objects in Images and Videos using Graphs and Fuzzy Models of Content Knowledge
%D 2016
%A Spina, Thiago Vallin,
%A Falcão, Alexandre Xavier,
%@affiliation Institute of Computing - University of Campinas
%@affiliation Institute of Computing - 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 Interactive image and video segmentation, graph-based image processing, fuzzy object models, object tracking, pose estimation.
%X Interactive segmentation is often necessary for image and video editing applications, which demand for effective and efficient methods capable of aiding the user to accurately extract objects of interest from the background with minimum involvement. The main goal is to place those objects on to new target images and videos, thereby avoiding the need to use green screens to acquire the footage. In this PhD research, we have devised methods that may be used by amateurs and professionals alike for interactive image and video segmentation, aiming to minimize the users effort and time required to obtain an accurate result. In particular, we have developed two methods for interactive image segmentation, and one for interactive video segmentation that outperforms/competes with a state-of- the-art commercial software. Our methods have also aided in interdisciplinary research with Geology, Psychology/Psychiatry (body pose estimation for early Autism assessment), and 3D medical imaging.
%@language en
%3 tvspina-phd-thesis-WTD.pdf