A framework that constructs an adaptive region similarity network from an initial segmentation using color and texture features and applies community detection algorithms to produce the final image segmentation, with tests on the Berkeley dataset showing improved performance.
K., Labatut, V., and Cherifi, H
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A General Framework for Complex Network-Based Image Segmentation
A framework that constructs an adaptive region similarity network from an initial segmentation using color and texture features and applies community detection algorithms to produce the final image segmentation, with tests on the Berkeley dataset showing improved performance.