首页 | 本学科首页   官方微博 | 高级检索  
     

基于空间语义对象混合学习的复杂图像场景自动分类方法研究
引用本文:孙显,付琨,王宏琦.基于空间语义对象混合学习的复杂图像场景自动分类方法研究[J].电子与信息学报,2011,33(2):347-354.
作者姓名:孙显  付琨  王宏琦
作者单位:1. 中国科学院电子学研究所,北京,100190
2. 中国科学院空间信息处理与应用系统技术重点实验室,北京,100190
基金项目:国家自然科学基金(41001285)资助课题
摘    要:场景分类是将多幅图像标记为不同语义类别的过程.该文针对现有方法对复杂图像场景分类性能欠佳的不足,提出一种新的基于空间语义对象混合学习的复杂图像场景分类方法.该方法以多尺度分割得到的图像对象而非整幅图像为主体进行产生式语义建模,统计各类有效特征挖掘对象的类别分布信息,并通过空间金字塔匹配,构建包含层次数据和语义信息的中间...

关 键 词:图像处理  场景分类  语义对象  混合学习  金字塔匹配
收稿时间:2010-04-12

Spatial Semantic Objects-based Hybrid Learning Method for Automatic Complicated Scene Classification
Sun Xian,Fu Kun,Wang Hong-qi.Spatial Semantic Objects-based Hybrid Learning Method for Automatic Complicated Scene Classification[J].Journal of Electronics & Information Technology,2011,33(2):347-354.
Authors:Sun Xian  Fu Kun  Wang Hong-qi
Affiliation:(Institute of Electronic, Chinese Academy of Sciences, Beijing 100190, China)  (Key Laboratory of Spatial Information Processing and Application System Technology, Chinese Academy of Sciences, Beijing 100190, China)
Abstract:Scene image classification refers to the task of grouping different images into semantic categories. A new spatial semantic objects-based hybrid learning method is proposed to overcome the disadvantages existing in most of the relative methods. This method uses generative model to deal with the objects obtained by multi-scale segmentation instead of whole image, and calculates kinds of visual features to mine the category information of every objects. Then, an intermediate vector is generated using spatial-pyramid matching algorithm, to describe both the layer data and semantic information and narrow down the “semantic gap”. The method also combines a discriminative learning procedure to train a more confident classifier. Experimental results demonstrate that the proposed method can achieve high training efficiency and classification accuracy in interpreting manifold and complicated images.
Keywords:Image processing  Scene classification  Semantic object  Hybrid learning  Pyramid matching
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《电子与信息学报》浏览原始摘要信息
点击此处可从《电子与信息学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号