UM  > 科技學院  > 電腦及資訊科學系
Bag of squares: A reliable model of measuring superpixel similarity
Zhang S.1; Feng W.1; Zhang J.1; Pun C.-M.2
2014-09-03
Conference Name2014 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)
Source PublicationProceedings - IEEE International Conference on Multimedia and Expo
Volume2014-September
IssueSeptmber
Conference DateJUL 14-18, 2014
Conference PlaceChengdu, CHINA
Abstract

As the increasing popularity of superpixel-based applications, measuring superpixel-level similarity becomes an important and commonly required problem. In this paper, we propose a general bag of squares (BoS) model for such particular purpose. Compared to existing methods, our approach provides a full scheme to both invariantly represent superpixels and accurately measure their pairwise similarities. In order to handle the split-and-merge variety of superpixels of same objects in different scenes, our model is based on superpixel pyramid. As a result, the BoS model of a superpixel is built upon a group of subregions consisting of the superpixel itself and its children subregions in the pyramid. For each subregion, we extract a proper number of maximum squares via distance transform, and then use a fast self-validated approach to clustering them into a small number of dominant squares, which together with a rotation and scale invariant square descriptor, jointly compose the BoS model for the particular superpixel. Finally, we measure the similarity between a pair of superpixels by the closeness of their BoS models. Experiments on interactive object segmentation and co-saliency detection show that the proposed BoS model can reliably capture the delicate differences among superpixels, thus always producing better segmentation results, especially for segmenting highly variant objects in clutter scenes.

KeywordBag Of Squares (Bos) Image Segmentation Scale And Rotation Invariance Superpixel-level Similarity
DOI10.1109/ICME.2014.6890320
URLView the original
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000360831800196
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.Tianjin University
2.Universidade de Macau
Recommended Citation
GB/T 7714
Zhang S.,Feng W.,Zhang J.,et al. Bag of squares: A reliable model of measuring superpixel similarity[C],2014.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang S.]'s Articles
[Feng W.]'s Articles
[Zhang J.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang S.]'s Articles
[Feng W.]'s Articles
[Zhang J.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang S.]'s Articles
[Feng W.]'s Articles
[Zhang J.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.