Certain object segmentation based on adaboost learning and nodes aggregation iterative graph-cuts

  • Authors:

  • Dongfeng Han;Wenhui Li;Xiaosuo Lu;Yi Wang;Xiaoqiang Zou

  • Affiliations:

  • College of Computer Science and Technology, Key Laboratory of Symbol, Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, P.R. China;College of Computer Science and Technology, Key Laboratory of Symbol, Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, P.R. China;College of Computer Science and Technology, Key Laboratory of Symbol, Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, P.R. China;College of Computer Science and Technology, Key Laboratory of Symbol, Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, P.R. China;College of Transportation, Jilin University, Changchun, P.R. China

  • Venue:
  • AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a fast automatic segmentation algorithm based on AdaBoost learning and iterative Graph-Cuts are shown. AdaBoost learning method is introduced for automatically finding the approximate location of certain object. Then an iterative Graph-Cuts method is used to model the segmentation problem. We call our algorithm as AdaBoost Aggregation Iterative Graph-Cuts (AAIGC). Compared to previous methods based on Graph-Cuts, our method is automatic. Once certain object is trained, our algorithm can cut it out from an image containing the certain object. The segmentation process is reliably computed automatically no additional users' efforts are required. Experiments are given and the outputs are encouraging