首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于高光谱图像的玉米种子特征提取与识别
引用本文:黄敏,朱晓,朱启兵,冯朝丽.基于高光谱图像的玉米种子特征提取与识别[J].光子学报,2012,41(7):-1-1.
作者姓名:黄敏  朱晓  朱启兵  冯朝丽
作者单位:江南大学轻工过程先进控制教育部重点实验室,江苏无锡,214122
基金项目:国家自然科学基金,江苏省自然科学基金,中国博士后基金,中央高校基本科研业务费专项基金
摘    要:玉米种子的形态特征是玉米品种识别的重要因素之一.采用高光谱成像系统获取9个品种共432粒玉米种子的高光谱反射图像,对图像进行校正和预处理,提取每个样本在563.6~911.4nm共55个波段范围内的形状特征.分别利用单波段、多波段和全波段下的玉米种子形状特征结合偏最小二乘判别法进行模型分类.结果显示,全波段范围内训练集和测试集的平均正确识别率达到98.31%和93.98%,均优于多波段和单波段的正确识别率.研究表明,该方法能充分利用高光谱图像中可见光和近红外区域的有效特征信息,较准确地鉴别玉米品种,为玉米品种的自动识别领域提供了一种新方法.

关 键 词:高光谱图像  玉米种子  形态特征  品种识别  偏最小二乘判别分析
收稿时间:2011/12/31

Morphological Characteristics of Maize Seed Extraction and Identification Based on the Hyperspectral Image
HUANG Min , ZHU Xiao , ZHU Qi-bing , FENG Zhao-li.Morphological Characteristics of Maize Seed Extraction and Identification Based on the Hyperspectral Image[J].Acta Photonica Sinica,2012,41(7):-1-1.
Authors:HUANG Min  ZHU Xiao  ZHU Qi-bing  FENG Zhao-li
Institution:(Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education), Jiangnan University,Wuxi,Jiangsu 214122,China)
Abstract:Morphological characteristic of maize seed is an important factor in identifying maize varieties. Hyperspectral images of 432 maize seeds including nine varieties were acquired using hyperspectral imaging system. The images were corrected and pre processed, and then shape features of each sample were extracted in the range of 563.6~911.4 nm including 55 wavelengths. The classification models were developed using the shape features of maize seeds from single wavelength, multi wavelengths and full wavelengths coupled with partial least squares discriminant analysis (PLSDA), respectively. Simulation results indicate that the average correct identification rate of training set and testing set with full wavelengths is 98.31% and 93.98%, which are better than single wavelength and multi wavelengths. Therefore, that is the accurate mean for identifying maize varieties using the feature information of visible and near infrared region from hyperspectral images.
Keywords:Hyperspectral images  Maize seed  Morphological characteristics  Species identification  Partial least squares discriminant analysis
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号