Multiple Class Segmentation Using A Unified Framework over Mean-Shift Patches

Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class object-based segmentation is achieved using the appearance and bag of keypoints models integrated over mean-shift patches. We...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2007 IEEE Conference on Computer Vision and Pattern Recognition Ročník 2007; číslo 4270254; s. 1 - 8
Hlavní autoři: Yang, Lin, Meer, Peter, Foran, David J.
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 16.07.2007
Témata:
Bayesian methods
Biomedical imaging
Biomedical informatics
Cancer
Clustering algorithms
Histograms
Image segmentation
Object recognition
Shape
Testing
ISBN:9781424411795, 1424411793
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class object-based segmentation is achieved using the appearance and bag of keypoints models integrated over mean-shift patches. We also propose a novel affine invariant descriptor to model the spatial relationship of keypoints and apply the elliptical Fourier descriptor to describe the global shapes. The algorithm is computationally efficient and has been tested for three real datasets using less training samples. Our algorithm provides better results than other studies reported in the literature.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISBN:9781424411795
1424411793
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2007.383229