arXiv Analytics

Sign in

arXiv:2002.05708 [cs.LG]AbstractReferencesReviewsResources

Simple Interactive Image Segmentation using Label Propagation through kNN graphs

Fabricio Aparecido Breve

Published 2020-02-13Version 1

Many interactive image segmentation techniques are based on semi-supervised learning. The user may label some pixels from each object and the SSL algorithm will propagate the labels from the labeled to the unlabeled pixels, finding object boundaries. This paper proposes a new SSL graph-based interactive image segmentation approach, using undirected and unweighted kNN graphs, from which the unlabeled nodes receive contributions from other nodes (either labeled or unlabeled). It is simpler than many other techniques, but it still achieves significant classification accuracy in the image segmentation task. Computer simulations are performed using some real-world images, extracted from the Microsoft GrabCut dataset. The segmentation results show the effectiveness of the proposed approach.

Journal: BREVE, Fabricio A. Simple Interactive Image Segmentation using Label Propagation through kNN graphs In: National Meeting on Artificial and Computational Intelligence (ENIAC'2017), 2017, Uberl\^andia, Minas Gerais, 2017
Categories: cs.LG, stat.ML
Related articles: Most relevant | Search more
arXiv:1810.10328 [cs.LG] (Published 2018-10-24)
Label Propagation for Learning with Label Proportions
arXiv:2002.06755 [cs.LG] (Published 2020-02-17)
Unifying Graph Convolutional Neural Networks and Label Propagation
arXiv:1909.03712 [cs.LG] (Published 2019-09-09)
Latent Multi-view Semi-Supervised Classification