CASIA OpenIR  > 智能感知与计算研究中心
基于泛化视觉词典图的物体识别方法
黄凯奇; 谭铁牛; 黄永祯; 王冲
2012-01-31
Date Available2012-07-25
CountryCN
Subtype发明
Abstract本发明公开了一种基于泛化视觉词典图编码的目标识别方法,包括以下步骤:对已经标好类别的目标图像进行特征提取,对提取的特征在视觉词典图上进行泛化编码,对编码结果进行训练并建模;对未知类别的图像进行特征提取,将提取的特征在视觉词典图上进行泛化编码,将编码结果输入到训练得到的模型,获得图像中目标的类别。该方法采用基于泛化视觉词典图的编码技术来提高分类精度,可用于智能视觉监控系统,使得监控系统能真正理解场景;可用于多媒体数字内容分析中的目标分析,判断目标的类别;可用于分析顾客对特定产品或者特定娱乐项目喜好。
Patent NumberCN201210021813.X
Status授权
Document Type专利
Identifierhttp://ir.ia.ac.cn/handle/173211/8660
Collection智能感知与计算研究中心
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
黄凯奇,谭铁牛,黄永祯,等. 基于泛化视觉词典图的物体识别方法. CN201210021813.X[P]. 2012-01-31.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[黄凯奇]'s Articles
[谭铁牛]'s Articles
[黄永祯]'s Articles
Baidu academic
Similar articles in Baidu academic
[黄凯奇]'s Articles
[谭铁牛]'s Articles
[黄永祯]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[黄凯奇]'s Articles
[谭铁牛]'s Articles
[黄永祯]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.