Sorry, you need to enable JavaScript to visit this website.

Implicit kernel presentation aware object segmentation framework

Citation Author(s):
Jincao Yao, Huimin Yu, Roland Hu
Submitted by:
Jincao Yao
Last updated:
20 March 2016 - 9:06am
Document Type:
Document Year:
Roland Hu

Given a set of training shapes and an input image with a shape similar to some of the elements in the training set, this poster introduces a new implicit kernel sparse model with a twofold goal. First, to obtain an implicit kernel sparse neighbor based combination that best represents the object. Second, to accurately segment the object taking into accounts both the high-level implicit kernel presentation and the low-level image information. A new energy function that combines the variational image segmentation with the implicit kernel presentation is introduced to accomplish both goals simultaneously.

1 user has voted: Jincao Yao