dc.contributor.authorWang, Junyan
dc.contributor.authorWang, Li
dc.contributor.authorChan, Kap Luk
dc.contributor.authorConstable, Martin
dc.date.accessioned2013-10-25T08:36:11Z
dc.date.available2013-10-25T08:36:11Z
dc.date.copyright2013en_US
dc.date.issued2013
dc.identifier.citationWang, J., Wang, L., Chan, K. L., & Constable, M. (2013). A linear programming based method for joint object region matching and labeling. 11th Asian Conference on Computer Vision, 66-78.en_US
dc.identifier.urihttp://hdl.handle.net/10220/16935
dc.description.abstractObject matching can be achieved by finding the superpixels matched across the image and the object template. It can therefore be used for detecting or labeling the object region. However, the matched superpixels are often sparsely distributed within the image domain, and there could therefore be a significant proportion of incorrectly detected or labeled regions even though there are few outlier matches. Consequently, the labeled regions may be unreliable for locating, extracting or representing the object. To address these problems, we propose to impose label priors that were previously incorporated in segmentation on the object matching. Specifically, in order to label as many regions as possible on the object, we propose to adopt the boundary-weighted smoothness prior. To reduce the singular outlier matches as much as possible, we propose to adopt the minimum description length principle adopted in segmentation. We then linearize the priors and incorporate them in the linear programming (LP) formulation of matching. The above gives rise to a novel general LP model for joint object region matching and labeling. This work extends the scope of conventional LP based object matching. The experimental results show that our method compares favorably to the LP based matching methods for object region labeling on a challenging dataset.en_US
dc.language.isoenen_US
dc.titleA linear programming based method for joint object region matching and labelingen_US
dc.typeConference Paper
dc.contributor.conferenceAsian Conference on Computer Vision (11th : 2013)en_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.contributor.schoolSchool of Art, Design and Mediaen_US
dc.identifier.doihttp://dx.doi.org/10.1007/978-3-642-37444-9_6


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record