Enhanced figure-ground classification with background prior propagation
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 7004799 |
Pages (from-to) | 873-885 |
Journal / Publication | IEEE Transactions on Image Processing |
Volume | 24 |
Issue number | 3 |
Online published | 8 Jan 2015 |
Publication status | Published - Mar 2015 |
Link(s)
DOI | DOI |
---|---|
Attachment(s) | Documents
Publisher's Copyright Statement
|
Link to Scopus | https://www.scopus.com/record/display.uri?eid=2-s2.0-84921862972&origin=recordpage |
Permanent Link | https://scholars.cityu.edu.hk/en/publications/publication(e2955238-aa72-48ea-97f6-db50cc06dffd).html |
Abstract
We present an adaptive figure-ground segmentation algorithm that is capable of extracting foreground objects in a generic environment. Starting from an interactively assigned background mask, an initial background prior is defined and multiple soft-label partitions are generated from different foreground priors by progressive patch merging. These partitions are fused to produce a foreground probability map. The probability map is then binarized via threshold sweeping to create multiple hard-label candidates. A set of segmentation hypotheses is formed using different evaluation scores. From this set, the hypothesis with maximal local stability is propagated as the new background prior, and the segmentation process is repeated until convergence. Similarity voting is used to select a winner set, and the corresponding hypotheses are fused to yield the final segmentation result. Experiments indicate that our method performs at or above the current state-of-the-art on several data sets, with particular success on challenging scenes that contain irregular or multiple-connected foregrounds.
Research Area(s)
- Image segmentation, multiple hypotheses fusion, similarity voting
Citation Format(s)
Enhanced figure-ground classification with background prior propagation. / Chen, Yisong; Chan, Antoni B.
In: IEEE Transactions on Image Processing, Vol. 24, No. 3, 7004799, 03.2015, p. 873-885.
In: IEEE Transactions on Image Processing, Vol. 24, No. 3, 7004799, 03.2015, p. 873-885.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Download Statistics
No data available