Please wait a minute...
浙江大学学报（农业与生命科学版）
浙江大学学报(农业与生命科学版)  2011, Vol. 37 Issue (2): 175-180    DOI: 10.3785/j.issn.1008-9209.2011.02.009
农业科学     
基于高光谱图像技术的油菜籽品种鉴别方法研究
邹伟,方慧,刘飞,周康韵,鲍一丹,何勇
浙江大学生物系统工程与食品科学学院 , 浙江杭州 310029
Identification of rapeseed varieties based on hyperspectral imagery
ZOU Wei,FANG Hui,ZHOU Kang-yun,BAO Yi-dan,HE Yong
School of Biosystem Engineering and Food Science , Zhejiang University , Hangzhou 310029 ,China
 全文: PDF(2766 KB)   HTML ( ) 
摘要： 提出了一种采用高光谱图像技术结合人工神经网络对油菜籽品种进行鉴别的方法 . 采集多个品种油菜籽400~1000nm 范围的高光谱图像数据 , 通过主成分分析法 (PCA) 获得主成分图像 , 确定特征波长 ; 采用基于灰度直方图和灰度共生矩阵联合的统计方法从特征图像中提取纹理特征参数 , 应用人工神经网络建立油菜籽品种鉴别模型 . 结果表明 , 模型训练时品种判别率为93.75%, 预测的判别率为91.67%. 说明高光谱图像技术对油菜籽品种具有较好的分类和鉴别作用 .
Abstract: Identification of rapeseed varieties by using hyperspectral imaging technique combined with artificial neural network (ANN) was proposed . Hyperspectral images of several rapeseed varieties in range 400-1000nm were acquired ,and then the principal component analysis (PCA) was performed to select three optimal band images .The texture parameters were extracted from the optimal band images based on gray level histogram and gray level co ‐ occurrence matrix (GLCM) statistical methods . The ANN modelwas usedfor theidentificationof rapeseedvarieties .Detection resultsof ANN modelshowed that the discriminating rates of rapeseed varieties in the training and prediction sets were 93.75% and 91.67%, respectively . It is indicated that the hyperspectral imaging technology has a good classification and identification effects on rapeseed varieties .
出版日期: 2011-03-25
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

邹伟,方慧,刘飞,周康韵,鲍一丹,何勇. 基于高光谱图像技术的油菜籽品种鉴别方法研究[J]. 浙江大学学报(农业与生命科学版), 2011, 37(2): 175-180.

ZOU Wei,FANG Hui,ZHOU Kang-yun,BAO Yi-dan,HE Yong. Identification of rapeseed varieties based on hyperspectral imagery. Journal of Zhejiang University: Agric. & Life Sci., 2011, 37(2): 175-180.

链接本文:

http://www.zjujournals.com/agr/CN/10.3785/j.issn.1008-9209.2011.02.009    或    http://www.zjujournals.com/agr/CN/Y2011/V37/I2/175

No related articles found!