Interactive segmentation based on iterative learning for multiple-feature fusion

NEUROCOMPUTING

卷:135

Article

Zhou, Lei¹  Qiao, Yu¹  Li, Yijun¹  He, Xiangjian^2,3  Yang, Jie¹ 

[1] Shanghai Jiao Tong Univ, Shanghai 200030, Peoples R China

[2] Univ Technol Sydney, Comp Vis & Recognit Lab, Sydney, NSW 2007, Australia

[3] Univ Technol Sydney, Res Ctr Innovat IT Serv & Applicat iNEXT, Sydney, NSW 2007, Australia

关键词: Interactive object segmentation;    Conditional random field;    Parameter learning;    Active learning;   

DOI  :  10.1016/j.neucom.2013.12.026

来源: Elsevier

【 摘 要 】

paper proposes a novel interactive segmentation method based on conditional random field (CRF) model to utilize the location and color information contained in user input. The CRF is configured with the optimal weights between two features, which are the color Gaussian Mixture Model (GMM) and probability model of location information. To construct the CRF model, we propose a method to collect samples for the cuttraining tasks of learning the optimal weights on a single image's basis and updating the parameters of features. To refine the segmentation results iteratively, our method applies the active learning strategy to guide the process of CRF model updating or guide users to input minimal training data for training the optimal weights and updating the parameters of features. Experimental results show that the proposed method demonstrates qualitative and quantitative improvement compared with the state-of-the-art interactive segmentation methods. The proposed method is also a convenient tool for interactive object segmentation. (C) 2014 Elsevier B.V. All rights reserved.

【 授权许可】

Free