Identification of Varieties of Black Bean Using Ground Based Hyperspectral Imaging
ZHANG Chu1, LIU Fei1, ZHANG Hai-liang1, 2, KONG Wen-wen1, HE Yong1*
1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China 2. School of Mechatronics Engineering, East China Jiaotong University, Nanchang 330013, China
摘要: 基于近地高光谱成像技术结合化学计量学方法,实现了黑豆品种的鉴别。实验以三种不同颜色豆芯的黑豆为研究对象,采用高光谱成像系统采集380~1 030 nm波段范围的高光谱图像,提取高光谱图像中的样本感兴趣区域平均光谱信息作为样本的光谱进行分析,建立黑豆品种的判别分析模型。共采集180个黑豆样本的180条平均光谱曲线。剔除明显噪声部分之后以440~943 nm范围光谱为黑豆样本的光谱,采用多元散射校正(multiplicative scatter correction,MSC)对光谱曲线进行预处理。分别以全部光谱数据、主成分分析(principal component analysis,PCA)提取的光谱特征信息、小波分析(wavelet transform,WT)提取的光谱特征信息建立了偏最小二乘判别分析法(partial least squares discriminant analysis,PLS-DA),簇类独立模式识别法(soft independent modeling of class analogy,SIMCA),最邻近节点算法(K-nearest neighbor algorithm,KNN),支持向量机(support vector machine,SVM), 极限学习机(extreme learning machine,ELM)等判别分析模型。以全谱的判别分析模型中,ELM模型效果最优;以PCA提取的光谱特征信息建立的模型中,ELM模型也取得了最优的效果;以WT提取的光谱特征信息建立的模型中,ELM模型结识别效果最好,建模集和预测集识别正确率达到100%。在所有的判别分析模型中,WT-ELM模型取得了最优的识别效果。实验结果表明以高光谱成像技术对黑豆品种进行无损鉴别是可行的,且WT用于提取光谱特征信息以及ELM模型用于判别黑豆品种能取得较好的效果。
关键词:黑豆;高光谱成像;判别分析模型
Abstract:In the present study, hyperspectral imaging combined with chemometrics was successfully proposed to identify different varieties of black bean. The varieties of black bean were defined based on the three different colors of the bean core. The hyperspectral images in the spectral range of 380~1 030 nm of black bean were acquired using the developed hyperspectral imaging system, and the reflectance spectra were extracted from the region of interest (ROI) in the images. The average spectrum of a ROI of the sample in the images was used to represent the spectrum of the sample and build classification models. In total, 180 spectra of 180 samples were extracted. The wavelengths from 440 to 943 nm were used for analysis after the removal of the spectral region with absolute noises, and 440~943 nm spectra were preprocessed by multiplicative scatter correction (MSC). Five classification methods, including partial least squares discriminant analysis (PLS-DA), soft independent modeling of class analogy (SIMCA), K-nearest neighbor algorithm (KNN), support vector machine (SVM) and extreme learning machine (ELM), were used to build discriminant models using the preprocessed full spectra, the feature information extracted by principal component analysis (PCA) and the feature information extracted by wavelet transform (WT) from the preprocessed spectra, respectively. Among all the classification models using the preprocessed full spectra, ELM models obtained the best performance; among all the classification models using the feature information extracted from the preprocessed spectra by PCA, ELM model also obtained the best classification accuracy; and among all the classification models using the feature information extracted from the preprocessed spectra by WT, ELM models obtained the best classification performance with 100% accuracy in both the calibration set and the prediction set. Among all classification models, WT-ELM model obtained the best classification accuracy. The overall results indicated that it was feasible to identify black bean varieties nondestructively by using hyperspectral imaging, and WT could effectively extract feature information from spectra and ELM algorithm was effective to build high performance classification models.
Key words:Black bean;Hyperspectral imaging;Discriminant model
张 初1,刘 飞1,章海亮1,2,孔汶汶1,何 勇1* . 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(03): 746-750.
ZHANG Chu1, LIU Fei1, ZHANG Hai-liang1, 2, KONG Wen-wen1, HE Yong1* . Identification of Varieties of Black Bean Using Ground Based Hyperspectral Imaging. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(03): 746-750.
[1] CONG Jian-ming(丛建明). Science and Technology of Food Industry(食品工业科技), 2008, (4): 262. [2] LI Wen-bin(李文斌). Food Engineering(食品工程), 2010, (4): 19. [3] LIU Yang, GUO Xiao-yu, SUN Dian-kui, et al(刘 洋, 郭晓雨, 孙殿奎等). Ginseng Research(人参研究), 2012, 24(1): 21. [4] ZHANG Ze-sheng, LIN Ji-wei, WANG Zhi-ping, et al(张泽生, 林纪伟, 王志平,等). Food Research and Development(食品研究与开发), 2012, 33(5): 143. [5] HONG Di-qing, GAO Chen-xi, WANG Shi-qing(洪迪清, 高晨曦, 王世清). China Pharmaceuticals(中国药业), 2007, 16(4): 55. [6] Zhang X L, Liu F, He Y, et al. Sensors-Basel, 2012, 12: 17234. [7] ZOU Wei, FANG Hui, LIU Fei, et al(邹 伟, 方 慧, 刘 飞,等). Journal of Zhejiang University·Agriculture & Life Sciences(浙江大学学报·农业与生命科学版), 2011, 37(2): 175. [8] Zhu D Z, Wang C, Pang B S, et al. J. Nanoelectron. Optoe.,2012, 7: 167. [9] Kamruzzaman M, ElMasry G, Sun D W, et al. J. Food Eng., 2011, 104(3): 332. [10] WU Jing-zhu, WANG Yi-ming, ZHANG Xiao-chao, et al(吴静珠, 王一鸣, 张小超,等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2006, 37(4): 80. [11] Luna A S, da Silva A P, Pinho J S, et al. Spectrochim Acta A, Mol. Biomol. Spectrosc., 2013, 100: 115. [12] Vitale R, Bevilacqua M, Bucci R, et al. Chemometr. Intell. Lab., 2013, 121: 90. [13] Balabin R M, Safieva R Z, Lomakina E I. Microchem. J., 2011, 98(1): 121. [14] De la Haba M, Fernández Pierna J, Fumière O, et al. J. Near Infrared Spec., 2007, 15(2): 81. [15] LI Ruo-cheng, XU Wen-fang, HUA Ying-jie(李若诚, 许文方, 华英杰). Journal of Changchun University of Technology(长春工业大学学报·自然科学版), 2012, 33(3): 269. [16] TIAN Gao-you, YUAN Hong-fu, LIU Hui-ying, et al(田高友, 袁洪福, 刘慧颖,等). Journal of Instrumental Analysis(分析测试学报), 2005, (1): 17. [17] Liu F, He Y, Wang L, et al. Food Bioprocess Tech., 2011, 4(8): 1331.