CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
基于HSI颜色空间的棉花杂质高速实时检测方法
高伟; 王志衡; 赵训坡; 孙凤梅
Source Publication自动化学报
2008
Volume34Issue:7Pages:729-735
Other Abstract
E±cient detection and separation of cotton contamination is important for controlling the quality of cotton. A robust and e±cient method of detecting the contamination in cotton is proposed. In this method, 3D-LUT is used to reduce the time of transformation between di®erent color spaces. Cotton contamination is detected based on the discrimination of hue and saturation in HSI color space between cotton ¯bers and cotton contamination. Color motion compensation is used to improve the spatial correction and reduce the wrong recognition rate. The experiments show that our system can complete the total process of image capturing, format transformation and impurities identi¯cation in 10 ms. Under a velocity of the cotton at 18 m/s, the recognition rate can reach as high as 95.4% with an impurity size of 2 £ 2 mm2.
KeywordHsi 颜色空间
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15328
Collection模式识别国家重点实验室_机器人视觉
Corresponding Author高伟
Affiliation中国科学院自动化研究所
First Author Affilication中国科学院自动化研究所
Corresponding Author Affilication中国科学院自动化研究所
Recommended Citation
GB/T 7714
高伟,王志衡,赵训坡,等. 基于HSI颜色空间的棉花杂质高速实时检测方法[J]. 自动化学报,2008,34(7):729-735.
APA 高伟,王志衡,赵训坡,&孙凤梅.(2008).基于HSI颜色空间的棉花杂质高速实时检测方法.自动化学报,34(7),729-735.
MLA 高伟,et al."基于HSI颜色空间的棉花杂质高速实时检测方法".自动化学报 34.7(2008):729-735.
Files in This Item: Download All
File Name/Size DocType Version Access License
基于HSI颜色空间的棉花杂质高速实时检测(3138KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[高伟]'s Articles
[王志衡]'s Articles
[赵训坡]'s Articles
Baidu academic
Similar articles in Baidu academic
[高伟]'s Articles
[王志衡]'s Articles
[赵训坡]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[高伟]'s Articles
[王志衡]'s Articles
[赵训坡]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于HSI颜色空间的棉花杂质高速实时检测方法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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