[1]王新忠,卢青,张晓东,等.基于高光谱图像的黄瓜种子活力无损检测[J].江苏农业学报,2019,(05):1197-1202.[doi:doi:10.3969/j.issn.1000-4440.2019.05.028]
　WANG Xin-zhong,LU Qing,ZHANG Xiao-dong,et al.Non-destructive detection of cucumber seeds vigor based on hyperspectral imaging[J].,2019,(05):1197-1202.[doi:doi:10.3969/j.issn.1000-4440.2019.05.028]
点击复制

基于高光谱图像的黄瓜种子活力无损检测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年05期
页码:
1197-1202
栏目:
园艺
出版日期:
2019-10-31

文章信息/Info

Title:
Non-destructive detection of cucumber seeds vigor based on hyperspectral imaging
作者:
王新忠1; 2; 卢青1; 2; 张晓东1; 2; 吴又新1; 2; 承银辉1; 2
(1.江苏大学农业装备工程学院，江苏镇江212013；2.江苏大学现代农业装备与技术教育部重点实验室，江苏镇江212013)
Author(s):
WANG Xin-zhong1; 2; LU Qing1; 2; ZHANG Xiao-dong1; 2; WU You-xin1; 2; CHENG Yin-hui1; 2
(1.College of Agricultural Equipment Engineering， Jiangsu University， Zhenjiang 212013， China;2.Key Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education, Jiangsu University, Zhenjiang 212013, China)
关键词:
高光谱图像; 种子活力; 主成分分析; 连续投影算法; 支持向量机
Keywords:
hyperspectral image; seed vigor; principal component analysis; successive projections algorithm; support vector machine
分类号:
S625.5
DOI:
doi:10.3969/j.issn.1000-4440.2019.05.028
文献标志码:
A
摘要:
为实现对黄瓜种子的快速、无损检测，以人工老化0 h、36 h、72 h的3个不同活力梯度的黄瓜种子为研究对象，利用波长400～1 000 nm的可见光光谱对黄瓜种子活力进行检测。对比了多元散射校正(MSC)、标准正态变换(SNV)、卷积平滑(S-G)3种预处理方法，结果显示SNV预处理的效果最优。从特征提取和特性选择2个角度进行降维分析。分别使用主成分分析法和连续投影算法，对比各个主成分数的正确分类率，选取最佳的主成分数。通过连续投影算法(SPA)选择9、12、13个特征波长，通过对比分类正确率，选出最佳波长数为12个。最后将提取出的最佳主成分和选择的最佳特征波长作为支持向量机的输入，分别选择线性核函数和径向基核函数，结合网格搜索方法，确定模型的惩罚因子c和径向基核函数中的参数gamma，建立判别分析模型。所有模型分类正确率均达到97.3%以上，其中SPA-SVM(基于RBF核函数)效果最佳，分类正确率达到98.6%。可见，利用高光谱图像技术结合SPA-SVM能有效地鉴别黄瓜种子的活力。
Abstract:
To detect the cucumber seeds rapidly, precisely and nondestructively, the cucumber seeds were subjected to three different gradient aging treatments of 0 h, 36 h, and 72 h. The seeds were detected using visible light spectra with wavelengths ranging from 400 nm to 1 000 nm. The three pretreatment methods of multiplicative scatter correction (MSC), Savitzky-Golay(S-G) and standard normal variate (SNV) were compared. The result showed that the effect of standard normal variate method was optimal. It was dimensionality-analyzed from two aspects: feature extraction and feature selection. Principal component analysis and continuous projection algorithm were used to compare the correct classification rate under each principal component number, and the optimal principal component number was chosen. The nine, twelve and thirteen characteristic wavelengths were selected by successive projection algorithm (SPA), and the optimal wavelength was selected by comparing the correct classification rate to 12. Finally, the extracted optimal principal component and the selected optimal feature wavelength were used as the input of the support vector machine, and the linear kernel function and the radial basis kernel function were selected, respectively. Moreover, the grid search method was combined to determine the penalty factor of the model and the parameter in the radial basis kernel function, and the discriminant analysis model was established. The classification accuracy of all models was above 97.3%, the SPA-SVM (based on RBF kernel function) had the best effect, and the correct classification rate reached 98.6%. It can be seen that the use of hyperspectral image technology combined with SPA-SVM can effectively identify the vigor of cucumber seeds.

参考文献/References:

[1]雷雨, 韩德俊, 曾庆东, 等. 基于高光谱成像技术的小麦条锈病病害程度分级方法[J]. 农业机械学报, 2018, 49(5):233-239.
[2]朱大洲, 王坤, 周光华, 等. 单粒大豆的近红外光谱特征及品种鉴别研究[J]. 光谱学与光谱分析, 2010, 30(12):3217-3221.
[3]姚侠妹, 张瑞娥, 偶春, 等. 人工老化处理对桔梗种子生理生化特性的影响[J]. 西北农林科技大学学报(自然科学版), 2015, 43(2):203-209.
[4]张瑛, 滕斌, 吴敬德, 等.水稻种子高温高湿人工加速老化试验方法研究[J]. 中国粮油学报, 2010, 25(10):8-12.
[5]崔鸿文. 黄瓜种子人工老化过程中某些生理生化规律研究[J]. 西北农林科技大学学报(自然科学版), 1992, 20(1):51-54.
[6]梁琨, 杜莹莹, 卢伟, 等. 基于高光谱成像技术的小麦籽粒赤霉病识别[J]. 农业机械学报, 2016, 47(2):309-315.
[7]HUANG M, TANG J, YANG B, et al. Classification of maize seeds of different years based on hyperspectral imaging and model updating[J]. Computers & Electronics in Agriculture, 2016, 122:139-145.
[8]WAKHOLI C, KANDPAL L M, LEE H, et al. Rapid assessment of corn seed viability using short wave infrared line-scan hyperspectral imaging and chemometrics[J]. Sensors and Actuators B: Chemical,2017, 255:498-507.
[9]AMBROSE A, KANDPAL L M, KIM M S, et al. High speed measurement of corn seed viability using hyperspectral imaging[J]. Infrared Physics & Technology, 2016, 75:173-179.
[10]NANSEN C, ZHAO G, DAKIN N, et al. Using hyperspectral imaging to determine germination of native Australian plant seeds[J]. J PhotochemPhotobiol B, 2015, 145:19-24.
[11]姚侠妹，张瑞娥，偶春, 等. 人工老化处理对桔梗种子生理生化特性的影响[J]. 西北农林科技大学学报(自然科学版), 2015, 43(2):203-209.
[12]张帅堂, 王紫烟, 邹修国, 等. 基于高光谱图像和遗传优化神经网络的茶叶病斑识别[J]. 农业工程学报, 2017,33(22):200-207.
[13]马惠玲, 蔡骋, 王若琳, 等. 一种基于高光谱成像的苹果品种快速鉴别方法[J]. 农业机械学报, 2017,48(4):305-312.
[14]赵欣欣, 宋丽荣, 权薇竹, 等. 高温高湿老化处理对不同豆类种子活力及生长能力的影响[J]. 作物杂志, 2017(5):168-172.
[15]SHRESTHA S, MATEJ K, ZIBRAT U,et al. Single seed near-infrared hyperspectral imaging in determining tomato (Solanum lycopersicum L.) seed quality in association with multivariate data analysis[J]. Sensors and Actuators B: Chemical, 2016, 237:1027-1034.
[16]KANDPAL L M, LOHUMI S, KIM M S, et al. Near-infrared hyperspectral imaging system coupled with multivariate methods to predict viability and vigor in muskmelon seeds[J]. Sensors & Actuators B Chemical, 2016, 229:534-544.
[17]孙俊, 路心资, 张晓东, 等. 基于高光谱图像的红豆品种GA-PNN神经网络鉴别[J]. 农业机械学报, 2016, 47(6):215-221.
[18]孙俊, 金夏明, 毛罕平, 等. 高光谱图像技术在掺假大米检测中的应用[J]. 农业工程学报, 2014, 30(21):301-307.
[19]张初，刘飞，章海亮，等．近地高光谱成像技术对黑豆品种无损鉴别［J］．光谱学与光谱分析， 2014，34(3):746-750．
[20]袁莹, 王伟, 褚璇, 等. 光谱特征波长的SPA选取和基于SVM的玉米颗粒霉变程度定性判别[J]. 光谱学与光谱分析, 2016, 36(1):226-230.
[21]孙俊, 张梅霞, 毛罕平, 等. 基于高光谱图像的桑叶农药残留种类鉴别研究[J]. 农业机械学报, 2015,46(6):251-256.
[22]李波，刘占宇，黄敬峰，等．基于PCA 和PNN 的水稻病虫害高光谱识别［J］．农业工程学报， 2009，25(9): 143-147．
[23]刘飞，张帆，方慧，等．连续投影算法在油菜叶片氨基酸总量无损检测中的应用［J］．光谱学与光谱分析，2009，29(11):3079-3093．
[24]章海亮，刘雪梅，何勇． SPA-LS-SVM 检测土壤有机质和速效钾研究［J］．光谱学与光谱分析，2014，34(5):1348-1351．

相似文献/References:

[1]苗荣慧,黄锋华,杨华,等.基于空谱一体化的农田高光谱图像分类[J].江苏农业学报,2018,(04):818.[doi:doi:10.3969/j.issn.1000-4440.2018.04.015]
　MIAO Rong-hui,HUANG Feng-hua,YANG hua,et al.Farmland classification of hyperspectral image based on spatial-spectral integration method[J].,2018,(05):818.[doi:doi:10.3969/j.issn.1000-4440.2018.04.015]
[2]潘威,杨晓东,乔雨,等.抗冷测定法评价烟草种子活力[J].江苏农业学报,2020,(02):312.[doi:doi:10.3969/j.issn.1000-4440.2020.02.009]
　PAN Wei,YANG Xiao-dong,QIAO Yu,et al.Research on tobacco seeds vigor by cold resistance measurement[J].,2020,(05):312.[doi:doi:10.3969/j.issn.1000-4440.2020.02.009]

备注/Memo

备注/Memo:
收稿日期：2019-04-11 基金项目：国家自然科学基金项目(61771224)；江苏省重点研发计划项目(BE2016323) 作者简介： 王新忠(1969-)，男，河北石家庄人，博士，教授，主要从事农业设施装备研究。(E-mail)xzwang@Ujs.edu.cn 通讯作者：卢青，(Tel)18605243646
更新日期/Last Update: 2019-11-11