We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Image segmentation via foreground and background semantic descriptors.
- Authors
Ding Yuan; Jingjing Qiang; Jihao Yin
- Abstract
In the field of image processing, it has been a challenging task to obtain a complete foreground that is not uniform in color or texture. Unlike other methods, which segment the image by only using low-level features, we present a segmentation framework, in which high-level visual features, such as semantic information, are used. First, the initial semantic labels were obtained by using the nonparametric method. Then, a subset of the training images, with a similar foreground to the input image, was selected. Consequently, the semantic labels could be further refined according to the subset. Finally, the input image was segmented by integrating the object affinity and refined semantic labels. State-of-the-art performance was achieved in experiments with the challenging MSRC 21 dataset.
- Subjects
IMAGE segmentation; SEMANTIC integration (Computer systems); COMPUTER vision; NONPARAMETRIC signal detection; MARKOV random fields
- Publication
Journal of Electronic Imaging, 2017, Vol 26, Issue 5, p1
- ISSN
1017-9909
- Publication type
Article
- DOI
10.1117/1.JEI.26.5.053004