Patent · US Active

Hybrid graph model for unsupervised object segmentation

US8238660B2 · kind B2 · utility

7Cited by

3References

19Claims

0Family size

Assignee

Microsoft Corporation · US

Inventors

Zhouchen Lin · Beijing, CN
Guangcan Liu · Beijing, CN
Xiaoou Tang · Sha Tin, CN

Key dates

Filing date	May 4, 2011
Grant date	Aug 7, 2012
Priority date	—
Expiry date	May 4, 2031

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/84
WIPO fieldComputer technology
WIPO sectorElectrical engineering

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.