中国邮电高校学报(英文) ›› 2017, Vol. 24 ›› Issue (2): 48-56.doi: 10.1016/S1005-8885(17)60197-3

• Artificial Intelligence • 上一篇    下一篇

GrabCut image segmentation algorithm based on structure tensor

张勇,袁家政,刘宏哲,李青   

  1. 北京联合大学
  • 收稿日期:2016-09-13 修回日期:2017-04-17 出版日期:2017-04-30 发布日期:2017-04-30
  • 通讯作者: 袁家政 E-mail:jiazheng@buu.edu.cn
  • 基金资助:
    国家自然基金:基于超图形XGML的图像半结构化研究;国家自然基金:图像内容的对象级语义标记及场景布局迁移;国家自然基金:面向视频社交网站的视频内容理解与挖掘研究;国家科技支撑:文化旅游资源挖掘与体验式平台研发与示范;国家科技支撑:数字文化旅游共性支撑技术研发与区域资源;北京市自然基金项目:海量社群图像语义分析与检索方法研究;北京市自然基金项目:基于视觉注意机制的3D视觉搜索研究

GrabCut image segmentation algorithm based on structure tensor

  • Received:2016-09-13 Revised:2017-04-17 Online:2017-04-30 Published:2017-04-30
  • Supported by:
    the National Natural Science Foundation of China (61372148, 61502036, 61571045, 71373023), the Beijing Advanced Innovation Center for Imaging Technology (BAICIT-2016002), the National Science and Technology Support Program (2014BAK08B02, 2015BAH55F03).

摘要: This paper attempts to present an interactive color natural images segmentation method. This method extracts the feature of images by using the nonlinear compact structure tensor (NCST) and then uses GrabCut method to obtain the segmentation. This method not only realizes the non-parametric fusion of texture information and color information, but also improves the efficiency of the calculation. Then, the improved GrabCut algorithm is used to evaluate the foreground target segmentation. In order to calculate the simplicity and efficiency, this paper also extends the Gaussian mixture model (GMM) constructed base on the GrabCut to the tensor space, and uses the Kullback-Leibler (KL) divergence instead of the usual Riemannian geometry. Lastly, an iteration convergence criterion is proposed to reduce the time of the iteration of GrabCut algorithm dramatically with satisfied segmentation accuracy. After conducting a large number of experiments on synthetic texture images and natural images, the results demonstrate that this method has a more accurate segmentation effect.

关键词: image segmentation, structure tensor, GrabCut, Kullback-Leibler, GMM

Abstract: This paper attempts to present an interactive color natural images segmentation method. This method extracts the feature of images by using the nonlinear compact structure tensor (NCST) and then uses GrabCut method to obtain the segmentation. This method not only realizes the non-parametric fusion of texture information and color information, but also improves the efficiency of the calculation. Then, the improved GrabCut algorithm is used to evaluate the foreground target segmentation. In order to calculate the simplicity and efficiency, this paper also extends the Gaussian mixture model (GMM) constructed base on the GrabCut to the tensor space, and uses the Kullback-Leibler (KL) divergence instead of the usual Riemannian geometry. Lastly, an iteration convergence criterion is proposed to reduce the time of the iteration of GrabCut algorithm dramatically with satisfied segmentation accuracy. After conducting a large number of experiments on synthetic texture images and natural images, the results demonstrate that this method has a more accurate segmentation effect.

Key words: image segmentation, structure tensor, GrabCut, Kullback-Leibler, GMM