基于最小噪声分离的籽棉异性纤维高光谱图像识别

针对籽棉表层多类难检异性纤维，包括纸屑、白发、丙纶丝、化纤和地膜等5种白色物质，采用高光谱技术和最小噪声分离（minimum noise fraction, MNF）分析方法对含有异性纤维的籽棉图像进行研究。该文在400～1000 nm的光谱范围内采集高光谱图像，根据光谱曲线选取子区域，应用最小噪声分离分析方法降维、去噪。取MNF变换后的前4幅分量图像，通过视觉评价，选定最佳成分图像并融合中值滤波、灰度变化等图像处理的方法确定最佳分割图像，提取异性纤维。试验结果表明，对于以上5种异性纤维，该方法的识别率达到91.0%。该研究可为棉花异性纤维检测系统的开发提供参考。...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 30; no. 9; pp. 243 - 248
Main Author 魏新华 吴姝 徐来齐 沈宝国 李玫瑾
Format Journal Article
LanguageChinese
Published 江苏大学现代农业装备与技术省部共建教育部重点实验室,镇江,212013%江苏省联合职业技术学院镇江分院,镇江,212016 2014
Subjects
图像处理
异性纤维
最小噪声分离
检测
棉花
降维
高光谱成像
image processing
detection
最小噪声分离
棉花
检测
foreign materials
cotton
高光谱成像
dimensionality reduction
hyper-spectral imaging
降维
图像处理
minimum noise fraction
异性纤维
Online AccessGet full text
ISSN1002-6819
DOI10.3969/j.issn.1002-6819.2014.09.030

Cover

More Information
Summary:针对籽棉表层多类难检异性纤维，包括纸屑、白发、丙纶丝、化纤和地膜等5种白色物质，采用高光谱技术和最小噪声分离（minimum noise fraction, MNF）分析方法对含有异性纤维的籽棉图像进行研究。该文在400～1000 nm的光谱范围内采集高光谱图像，根据光谱曲线选取子区域，应用最小噪声分离分析方法降维、去噪。取MNF变换后的前4幅分量图像，通过视觉评价，选定最佳成分图像并融合中值滤波、灰度变化等图像处理的方法确定最佳分割图像，提取异性纤维。试验结果表明，对于以上5种异性纤维，该方法的识别率达到91.0%。该研究可为棉花异性纤维检测系统的开发提供参考。
Bibliography:cotton;detection;image processing;foreign materials;hyper-spectral imaging;dimensionality reduction;minimum noise fraction
11-2047/S
In order to improve the recognition accuracy of seed cotton foreign fibers, the identification method in hyper-spectral images based on minimum noise fraction （MNF） was proposed and applied to feature extraction to reduce the dimension of multispectral images. This method can reduce the numbers of hyper-spectral data, and made the images noise reduce to the minimum and also reduce the computational requirements for subsequent processing. This paper selected white foreign fibers and cotton, which were in small discrimination, as the research object with 512 bands in the wavelength range of 400-1 000 nm. The spectral subset was selected according to the spectral curve, and then reducing dimension and denoising by using analysis method of MNF. The best component image was selected from the first four component images of MNF transformation by manual visual evaluation. The methods of i
ISSN:1002-6819
DOI:10.3969/j.issn.1002-6819.2014.09.030