A Bayesian Nonparametric Model for Hierarchical Sequence of Images

摘要：

　　Scale features are useful for a great number of applications in computer vision.However,it is difficult to tolerate diversities of features in natural scenes by parametric methods.Empirical studies show that object frequencies and segment sizes follow the power law distributions which are well generated by Pitman-Yor (PY) processes.Based on mid-level segments,we propose a hierarchical sequence of images to obtain scale information stored in a hierarchical structure through the hierarchical Pitman-Yor (HPY) model which is expected to tolerate uncertainty of natural images.We also evaluate our representation by the application of segmentation.

关键词： Hierarchical sequence Bayesian nonparametric Segmentation

作者: You-Hai QIU Xiang-Ping SUN Mary Fenghua She

作者单位: Institute for Frontier Materials,Deakin University,Waurn Ponds,Geelong,Victoria,3216,Australia

会议类型: 国内会议

会议名称: 2014年国际计算机科学与软件工程学术会议

会议地点: 杭州

会议语种:英文

页码: 1-7

在线出版日期: 2014-10-18（万方平台首次上网日期，不代表论文的发表时间）