中国科学院机构知识库网格系统: TextureGrow: Object recognition and segmentation with limit prior knowledge (EI CONFERENCE)

中国科学院机构知识库网格

Chinese Academy of Sciences Institutional Repositories Grid

TextureGrow: Object recognition and segmentation with limit prior knowledge (EI CONFERENCE)

文献类型：会议论文


作者	Yao Z. ; Han Q.
出版日期	2011
会议名称	2011 International Conference on Network Computing and Information Security, NCIS 2011, May 14, 2011 - May 15, 2011
会议地点	Guilin, Guangxi, China
关键词	In this paper we present a new method for automatically visual recognition and semantic segmentation of photographs. Our automatically and rapidly approach based on Cellular Automation. Most of the analysis and description of recognition and segmentation are based on statistical or structural properties of this attribute most of them need plenty of samples and prior Knowledge. In this paper within a few evident samples (not too many) we can first get the texture feature of each component and the structures then select the approximately location randomly of the objects or patches of them then we use the Cellular Automata algorithm to "grow" based on texture of different objects. The grow progress will stop When texture grow to the boundary. By this steps a new method is found which allow us use very few samples and low lever experience and get a rapidly and accuracy way to recognize and segment objects. We found that this new propose gives competitive results with limited experience and samples. 2011 IEEE.
页码	99-102
收录类别	EI
源URL	[http://ir.ciomp.ac.cn/handle/181722/33592]
专题	长春光学精密机械与物理研究所_中科院长春光机所知识产出_会议论文
推荐引用方式 GB/T 7714	Yao Z.,Han Q.. TextureGrow: Object recognition and segmentation with limit prior knowledge (EI CONFERENCE)[C]. 见:2011 International Conference on Network Computing and Information Security, NCIS 2011, May 14, 2011 - May 15, 2011. Guilin, Guangxi, China.

入库方式： OAI收割

来源：长春光学精密机械与物理研究所

浏览0

下载0

收藏0

其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。