基于高光谱成像技术结合PCA-GRNN 的糙米发芽率检测方法研究

于施淼; 卢伟; 梁琨; 洪德林; 党晓景

doi:doi:10.3788/lop52.113001

激光与光电子学进展, 2015, 52 (11): 113001, 网络出版: 2015-11-09

基于高光谱成像技术结合PCA-GRNN 的糙米发芽率检测方法研究下载： 535次

Study on Prediction of Germination Rate of Rice Seeds Using Hyperspectral Imaging Combined with PCA and GRNN

论文大纲

于施淼 ^1,*卢伟 ¹梁琨 ¹洪德林 ²党晓景 ²

作者单位

¹ 南京农业大学工学院江苏省现代设施农业技术与装备工程实验室, 江苏南京 210031

² 南京农业大学农学院作物遗传与种质创新国家重点实验室, 江苏南京 210095

AI 词云图 AI语音精读 AI语音超短摘要

注：本部分内容由 AI 自动生成，请您知悉。

摘要

水稻是人类的主要粮食作物，其发芽率是评定水稻质量的重要指标之一。以南粳46 为研究对象，利用高光谱成像技术预测剥壳后的稻种(以下简称糙米)发芽率。在400~1000 nm 波长范围内，采集960 粒饱满、无霉变糙米的高光谱图像，提取感兴趣区域的平均光谱曲线，利用主成分分析(PCA)提取特征波长，再结合偏最小二乘法(PLS)、反向传播神经网络(BPNN)、径向基神经网络(RBFNN)和广义回归网络(GRNN)4 种建模方法分别对糙米5 个区域特征波长的光谱数据建立预测模型并加以比较。4 种建模方法对糙米A 区域(含胚芽)的平均预测效果最好( R_p=0.970)，其中，GRNN 模型对该区域预测精度最高( R_p =0.982, f_RMSEP =0.978)。研究结果表明利用高光谱成像技术并结合PCA和GRNN 检测糙米发芽率是可行的。

Abstract

Rice is the main food crop for human beings, whose germination rate is one of the most important indexes to evaluate rice quality. The germination rate of brown rice named Nan Jing 46 is predicted by using hyperspectral imaging system. Hyperspectral images of 960 samples which are full and not moldy are captured, and the spectral region is from 400 nm to 1000 nm. The mean spectra are extracted from the region of interest of each image and principal component analysis (PCA) is applied to select characteristic wavelengths from the full- spectrum. The prediction models are established based on spectrum data of characteristic wavelengths of different rice parts using 4 prediction methods, including partial least squares (PLS), radial basis function neural network (RBFNN), general regression neural network (GRNN) and back-propagating neural network (BPNN). After repeated tests, the top area of brown rice (containing the germ) is chosen as the characteristic part, which has the best prediction performance ( R_p =0.970). The order of the prediction accuracy from low to high is PLS, BPNN, RBGNN, GRNN. Among these methods, GRNN has the highest prediction accuracy ( R_p=0.982, f_RMSEP =0.978). The results indicate that it is feasible to detect the germination rate of brown rice by the hyperspectral imaging system.

参考文献

[1] 赵国伟. 阐述提高水稻种子发芽率的措施[J]. 民营科技, 2014, 17: 195.

Zhao Guowei. Measures of how to enhance the germination rate of rice seeds[J]. Private Technology, 2014, 17: 195.

[2] 石亚萍, 蔡静平. 种子发芽率快速测定方法的研究进展[J]. 中国种业, 2008, 2: 13-14.

Shi Yaping, Cai Jingping. Study on rapid determination of seed germination rate[J]. Cereals and Oils Processing, 2008, 2: 13-14.

[3] Xiong Z, Sun D W, Dai Q, et al.. Application of visible hyperspectral imaging for prediction of springiness of fresh chicken meat[J]. Food Analytical Methods, 2015, 8(2): 380-391.

[4] Mahesh S, Jayas D S, Paliwal J, et al.. Comparison of partial least squares regression (PLSR) and principal components regression (PCR) methods for protein and hardness predictions using the near-infrared (NIR) hyperspectral images of bulk samples of Canadian wheat[J]. Food and Bioprocess Technology, 2015, 8(1): 31-40.

[5] 赵杰文, 惠喆, 黄林, 等. 高光谱成像技术检测鸡肉中挥发性盐基氮含量[J]. 激光与光电子学进展, 2013, 50(7): 073003.

Zhao Jiewen, Hui Zhe, Huang Lin, et al.. Quantitative detection of TVB- N content in chicken meat with hyperspectral imaging technology[J]. Laser & Optoelectronics Progress, 2013, 50(7): 073003.

[6] 张保华, 黄文倩, 李江波, 等. 用高光谱成像和PCA 检测苹果的损伤和早期腐烂[J]. 红外与激光工程, 2013, 42(S2): 279- 283.

Zhang Baohua, Huang Wenqian, Li Jiangbo, et al.. Detection of bruises and early decay in apples using hyperspectral imaging and PCA[J]. Infrared and Laser Engineering, 2013, 42(S2): 279-283.

[7] 张亚彪, 罗举, 唐健, 等. 不同品种水稻叶片的高光谱特征及其色素, 含水率分析[J]. 安徽农业科学, 2015, 43(7): 40-44.

Zhang Yabiao, Luo Ju, Tang Jian, et al.. Hyperspectral characteristics of rice leaves and their pigment and water content analysis[J]. Journal of Anhui Agricultural Sciences, 2015, 43(7): 40-44.

[8] Kong W, Zhang C, Liu F, et al.. Rice seed cultivar identification using near- infrared hyperspectral imaging and multivariate data analysis[J]. Sensors, 2013, 13(7): 8916-8927.

[9] 黄双萍, 齐龙, 马旭, 等. 基于高光谱成像的水稻穗瘟病害程度分级方法[J]. 农业工程学报, 2015, 31(1): 212-219.

Huang Shuangping, Qi Long, Ma Xu, et al.. Grading method of rice panicle blast severity based on hyperspectral image [J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(1): 212-219.

[10] 邓小琴, 朱启兵, 黄敏. 融合光谱、纹理及形态特征的水稻种子品种高光谱图像单粒鉴别[J]. 激光与光电子学进展, 2015, 52(2): 021001.

Deng Xiaoqin, Zhu Qibing, Huang Min. Variety discrimination for single rice seed by integrating spectral, texture and morphological features based on hyperspectral image[J]. Laser & Optoelectronics Progress, 2015, 52(2): 021001.

[11] 李美凌, 邓飞, 刘颖, 等. 基于高光谱图像的水稻种子活力检测技术研究[J]. 浙江农业学报, 2015, 27(1): 1-6.

Li Meiling, Deng Fei, Liu Ying, et al.. Study on detection technology of rice seed vigor based on hyperspectral image[J]. Acta Agriculturae Zhejiangensis, 2015, 27(1): 1-6.

[12] 李毅念, 姜丹, 刘璎瑛, 等. 基于近红外光谱的杂交水稻种子发芽率测试研究[J]. 光谱学与光谱分析, 2014, 34(6): 1528- 1532.

Li Yinian, Jiang Dan, Liu Yingying, et al.. Testing of germination rate of hybrid rice seeds based on near- infrared reflectance spectroscopy[J]. Spectroscopy and Spectral Analysis, 2014, 34(6): 1528-1532.

[13] 蔡健荣, 王建黑, 黄星奕, 等. 高光谱图像技术检测柑橘果锈[J]. 光电工程, 2009, 36(6): 26-30.

Cai Jianrong, Wang Jianhei, Huang Xingyi, et al.. Detection of rust in citrus with hyperspectral imaging technology[J]. Opto-Electronic Engineering, 2009, 36(6): 26-30.

[14] 刘民法, 张令标, 何建国, 等. 基于高光谱成像技术的长枣表面农药残留无损检测[J]. 食品与机械, 2014, 5: 87-92.

Liu Minfa, Zhang Lingbiao, He Jianguo, et al.. Study on non-destructive detection of pesticide residues on Lingwu long jujubes’surface using hyperspectral imaging[J]. Food & Machinery, 2014, 5: 87-92.

[15] 国家标准化技术委员会. GB/T 3543.1~3543.7-1995 农作物种子验证规程[S]. 北京: 中国标准出版社, 1995.

National Standardization Technical Committee. GB/T 3543.1~3543.7-1995 Rules for agricultural seed testing[S]. Beijing: China Standard Press, 1995.

[16] 陈全胜, 张燕华, 万新民, 等. 基于高光谱成像技术的猪肉嫩度检测研究[J]. 光学学报, 2010, 30(9): 2602-2607.

Chen Quansheng, Zhang Yanhua, Wan Xinmin, et al.. Study on detection of pork tenderness using hyperspectral imaging technique[J]. Acta Optica Sinica, 2010, 30(9): 2602-2607.

[17] Xiong Z, Sun D W, Dai Q, et al.. Application of visible hyperspectral imaging for prediction of springiness of fresh chicken meat[J]. Food Analytical Methods, 2015, 8(2): 380-391.

[18] 余晓娅, 张玉钧, 殷高方, 等. 基于偏最小二乘回归的藻类荧光光谱特征波长选取[J]. 光学学报, 2014, 34(9): 0930002.

Yu Xiaoya, Zhang Yujun, Yin Gaofang, et al.. Feature wavelength selection of phytoplankton fluorescence spectra based on partial least squares[J]. Acta Optica Sinica, 2014, 34(9): 0930002.

[19] 王冲冲, 胡立发, 何斌, 等. 基于神经网络的压电倾斜镜磁滞补偿方法研究[J]. 中国激光, 2013, 40(11): 1113001.

Wang Chongchong, Hu Lifa, He Bin, et al.. Hysteresis compensation method of piezoelectic steering mirror based on neural network[J]. Chinese J Lasers, 2013, 40(11): 1113001.

[20] 孙忠华, 王珏, 瞿中. 基于GA 的神经网络在火炸药剂辨识中的应用[J]. 微机发展, 2003, 13(8): 3-5.

Sun Zhonghua, Wang Jue, Qu Zhong. Application of neural networks based on GA to identification of loading materials for initiating explosive device[J]. Microcomputer Development, 2003, 13(8): 3-5.

[21] 刘载文, 李梦寻, 王小艺, 等. 基于LSSVM 和RBFNN 的水华中短期预测方法[J]. 计算机与应用化学, 2012, 29(10): 1189- 1194.

Liu Zaiwen, Li Mengxun, Wang Xiaoyi, et al.. The method of mid- term and short- term prediction for water bloom based on LSSVM and RBFNN[J]. Computer and Applied Chemistry, 2012, 29(10): 1189-1194.

[22] 刘波平, 秦华俊, 罗香, 等. PLS-GRNN 法近红外光谱多组分定量分析研究[J]. 光谱学与光谱分析, 2007, 27(11): 2216- 2220.

Liu Boping, Qin Huajun, Luo Xiang, et al.. Multicomponent quantitative analysis using near infrared spectroscopy by building PLS-GRNN model[J]. Spectroscopy and Spectral Analysis, 2007, 27(11): 2216-2220.

[23] 吴聚兰, 周小梅, 范玲娟, 等. 人工老化对大豆种子活力和生理生化特性的影响[J]. 中国油料作物学报, 2011, 33(6): 582- 587.

Wu Julan, Zhou Xiaomei, Fan Lingjuan, et al.. Effects of artificial aging on seed vigor, physiological and biochemical characteristics of soybean seeds[J]. Chinese Journal of Oil Crop Sciences, 2011, 33(6): 582-587.

[24] 程洪, 史智兴, 尹辉娟, 等. 基于机器视觉的多个玉米籽粒胚部特征检测[J]. 农业工程学报, 2013, 29(19): 145-151.

Cheng Hong, Shi Zhixing, Yin Huijuan, et al.. Detection of multi- corn kernel embryos characteristic using machine vision[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(19): 145-151.

[25] 蔡春菊, 范少辉, 刘凤, 等. 毛竹种子人工老化过程中生理生化变化[J]. 林业科学, 2013, 49(8): 29-34.

Cai Chunju, Fan Shaohui, Liu Feng, et al.. Physiological and biochemical changes of moso bamboo (Phyllostachys edulis) seeds in artificial aging[J]. Scientia Silvae Sinicae, 2013, 49(8): 29-34.

[26] 谭美莲, 校凝凝, 严明芳, 等. 人工老化对向日葵种子活力及生理特性的影响[J]. 安徽农业科学, 2010, 38(23): 12319-12322.

Tan Meilian, Xiao Ningning, Yan Mingfang, et al.. Effects of sun flower artificial aging on seed vigor and physiological characteristics[J]. Journal of Anhui Agricultural Sciences, 2010, 38(23): 12319-12322.

[27] 付艺峰, 李鸿雁, 黄帆, 等. 人工老化对老芒麦种子活力和生理生化变化的影响[J]. 植物遗传资源学报, 2014, 15(6): 1360- 1363.

Fu Yifeng, Li Hongyan, Huang Fan, et al.. Physiological and seed vigor changes of Elymus sibiricus L. seeds during artificial aging[J]. Journal of Plant Genetic Resources, 2014, 15(6): 1360-1363.

于施淼, 卢伟, 梁琨, 洪德林, 党晓景. 基于高光谱成像技术结合PCA-GRNN 的糙米发芽率检测方法研究[J]. 激光与光电子学进展, 2015, 52(11): 113001. Yu Shimiao, Lu Wei, Liang Kun, Hong Delin, Dang Xiaojing. Study on Prediction of Germination Rate of Rice Seeds Using Hyperspectral Imaging Combined with PCA and GRNN[J]. Laser & Optoelectronics Progress, 2015, 52(11): 113001.

基于高光谱成像技术结合PCA-GRNN 的糙米发芽率检测方法研究下载： 535次

关于本站 Cookie 的使用提示

全站搜索

基于高光谱成像技术结合PCA-GRNN 的糙米发芽率检测方法研究 下载： 535次

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于高光谱成像技术结合PCA-GRNN 的糙米发芽率检测方法研究下载： 535次