Fast semi-supervised image segmentation by novelty selection

Update item information
Publication Type Journal Article
School or College College of Engineering
Department Electrical & Computer Engineering
Creator Tasdizen, Tolga
Other Author Paiva, Antonio R. C.
Title Fast semi-supervised image segmentation by novelty selection
Date 2010
Description The goal of semi-supervised image segmentation is to obtain the segmentation from a partially labeled image. By utilizing the image manifold structure in labeled and unlabeled pixels, semi-supervised methods propagate the user labeling to the unlabeled data, thus minimizing the need for user labeling. Several semi-supervised learning methods have been proposed in the literature. Although results have been promising, these methods are very computationally intensive. In this paper, we propose novelty selection as a pre-processing step to reduce the number of data points while retaining the fundamental structure of the data. Since the computational complexity is a power of the number of points, it is possible to significantly reduce the overall computation requirements. Results in several images show that the computation time is greatly reduced without sacrifice in segmentation accuracy.
Type Text
Publisher Institute of Electrical and Electronics Engineers (IEEE)
First Page 1054
Last Page 1057
Language eng
Bibliographic Citation Paiva, A. R. C., & Tasdizen, T. (2010). Fast semi-supervised image segmentation by novelty selection. ICASSP, 1054-7.
Rights Management (c) 2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Format Medium application/pdf
Format Extent 315,736 bytes
Identifier ir-main,15209
ARK ark:/87278/s6zg79r8
Setname ir_uspace
Date Created 2012-06-13
Date Modified 2021-05-06
ID 705814
Reference URL
Back to Search Results