Hybrid graph model for unsupervised object segmentation

Details Hybrid graph model for unsupervised object segmentation Hybrid graph model for unsupervised object segmentation

2011-08-09

2011-08-09

Ahmed, Samir A (Department: 2624)

Image analysis

Image segmentation

C382S190000, C382S195000, C382S228000

Reexamination Certificate

active

07995841

ABSTRACT:
This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.

REFERENCES:
patent: 5825922 (1998-10-01), Pearson et al.
patent: 6731799 (2004-05-01), Sun et al.
patent: 6973212 (2005-12-01), Boykov et al.
patent: 2004/0140992 (2004-07-01), Marquering et al.
patent: 2005/0254546 (2005-11-01), Rittscher et al.
patent: 2007/0014473 (2007-01-01), Slabaugh et al.
patent: 2007/0122039 (2007-05-01), Zhang et al.
Zhuowen Tu et al. “Image Parsing: Unifying Segmentation, Detection, and Recognition”, 9th IEEE International Conference on Computer Vision, ICCV 2003.
S. Agarwal and D. Roth, “Learning a Sparse Representation for Object Detection,” Proc. European Conf. Computer Vision, pp. 113-130, 2002.
Mori, G., “Guiding model search using segmentation”, Tenth IEEE International Conference on Computer Vision, 2005. ICCV 2005. pp. 1417-1423 vol. 2.
Liangliang Cao; Li Fei-Fei, “Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes”, IEEE 11th International Conference on Computer Vision, 2007, pp. 1-8.
Liang Zhao; Davis, L.S., “Closely coupled object detection and segmentation”, 10th IEEE International Conference on Computer Vision, 2005, pp. 454-461, v.1.
Leibe, et al., “Combined Object Categorization and Segmentation with an Implicit Shape Model”, at <<http://citeseer.ist.psu.edu/cache/papers/cs/30764/http:zSzzSzwww.vision.ethz.chzSzpublzSzleibe-ism-slcv04.pdf/leibe04combined.pdf>>, ECCV, 2004, pp. 16.
Prasad, et al., “Learning Class-Specific Edges for Object Detection and Segmentation”, available at least as early as Jul. 3, 2007, at <<http://eprints.pascal-network.org/archive/00002295/01/prasad06a.pdf>>, pp. 11.
Tu, et al., “Recognizing Objects Using Color-Annotated Adjacency Graphs”, available at least as early as Jul. 3, 2007, at <<http://users.rsise.anu.edu.au/˜hartley/Papers/sicily/sicily.pdf>>, pp. 18.
Yang, et al., “Unsupervised Segmentation of Natural Images via Lossy Data Compression”, at <<http://www.eecs.berkley.edu/˜yang/publications/AllenYangCVIU07.pdf>>, Mar. 8, 2007, pp. 24.
Anonymous, “A Hybrid Graph Model for Unsupervised Object Segmentation”, ICCV 2007 Submission #372, 10 pages.

Affiliated with

Also associated with

Rating

Hybrid graph model for unsupervised object segmentation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Hybrid graph model for unsupervised object segmentation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hybrid graph model for unsupervised object segmentation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2676576