Share Email Print

Journal of Electronic Imaging • Open Access

Image segmentation via foreground and background semantic descriptors
Author(s): Ding Yuan; Jingjing Qiang; Jihao Yin

Paper 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.

Paper Details

Date Published: 9 September 2017
PDF: 8 pages
J. Electron. Imag. 26(5) 053004 doi: 10.1117/1.JEI.26.5.053004
Published in: Journal of Electronic Imaging Volume 26, Issue 5
Show Author Affiliations
Ding Yuan, Beihang Univ. (China)
Jingjing Qiang, Beihang Univ. (China)
Jihao Yin, Beihang Univ. (China)

© SPIE. Terms of Use
Back to Top