[ABE-L] Seminarios em High Dimensional Data Analysis.

[Ronaldo Dias]

Prezados(as),
Para aqueles que puderem participar.

Data: 12/06/2019
Local: sala 221 IMECC as 13hs

Expectation-maximization on graph-based image segmentation
(Jordão Bragantini, DE-Unicamp)

Currently, deep learning methods are able to achieve great results on
computer vision tasks but require a huge amount of labeled data.
Thus, images are labeled with user interaction, on these instances
graph-based algorithms are employed to decrease user effort.
With this, the image segmentation (graph partition) is view as EM problem
given the image graph restrictions and pixels characteristics.

Reference:
GrabCut - Interactive Foreground Extraction using Iterated Graph Cuts (em
anexo)


-- 
Ronaldo Dias, Ph.D.
Professor
Dept. of Statistics-IMECC, UNICAMP
www.ime.unicamp.br/~dias
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <https://lists.ime.usp.br/archives/abe/attachments/20190611/bd5de85f/attachment.html>