Invention Grant
US08842915B2 Connectivity similarity based graph learning for interactive multi-label image segmentation
有权
用于交互式多标签图像分割的基于连通性的图形学习
- Patent Title: Connectivity similarity based graph learning for interactive multi-label image segmentation
- Patent Title (中): 用于交互式多标签图像分割的基于连通性的图形学习
-
Application No.: US13260109Application Date: 2009-04-22
-
Publication No.: US08842915B2Publication Date: 2014-09-23
- Inventor: Bingfeng Zhou , Yadong Mu
- Applicant: Bingfeng Zhou , Yadong Mu
- Applicant Address: CN Beijing
- Assignee: Peking University
- Current Assignee: Peking University
- Current Assignee Address: CN Beijing
- Agency: Maschoff Brennan
- International Application: PCT/CN2009/071402 WO 20090422
- International Announcement: WO2010/121422 WO 20101028
- Main IPC: G06K9/34
- IPC: G06K9/34
Abstract:
A system and method of connectivity-based image processing to identify and extract objects in image data is described. Variations on the method may include iterative local smoothing operations and various algorithmic solutions to improve real-time processing. Variations may also include object extraction processes based on user-provided information about an object in an image.
Public/Granted literature
- US20120027300A1 CONNECTIVITY SIMILARITY BASED GRAPH LEARNING FOR INTERACTIVE MULTI-LABEL IMAGE SEGMENTATION Public/Granted day:2012-02-02
Information query
