Study on the Tea Identification of Near-Infrared Hyperspectral Image Combining Spectra-Spatial Information
CAI Qing-kong1, LI Er-jun2, JIANG Jin-bao3*, QIAO Xiao-jun3, JIANG Rui-bo1, FENG Hai-kuan4, 5, 6, LIU Shao-tang1, CUI Xi-min3
1. College of Civil Engineering, Henan University of Engineering, Zhengzhou 451191, China
2. College of Human and Social Sciences, Henan University of Engineering, Zhengzhou 451191, China
3. College of Geosciences and Surveying Engineering, China University of Mining and Technology, Beijing 100083, China
4. Beijing Research Center for Information Technology in Agriculture, Beijing 100097, China
5. National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China
6. Key Laboratory for Information Technologies in Agriculture and Rural Affairs, Beijing 100097, China
Abstract:The class-identification and grade-determination of tea have practical importance. Hyperspectral imaging possesses conspicuous advantages in data form of the combination of image and spectra, as well as in fast and undamaged checking in food safety, compared with traditional methods. In this study, hyperspectral images of four kinds of tea which have similar appearance were obtained at the spectral range from 1 000 to 2 500 nm. MNF (Minimum Noise Fraction) and NWFE (Nonparametric Weighted Feature Extraction) were used to rotate and project the hyperspectral data from high dimension to lower subspaces. Then, ANOVA (Analysis of Variance) was used to estimate and select the projected subspaces which have better separability, and they are MNF1, MNF2, MNF4, MNF6, MNF8,NWFE1, NWFE2. Then selected subspaces together with the sum of all original bands were fed to SVM classifier. On the other hand, Finally, IID (image intrinsic decomposition) was applied to decompose the original spectra into material reflectance spectra R and shadow spectra S. Next, gradient image was obtained from R, and watershed algorithm was adapted to segment image in spatial dimension. Finally, results of both pixel-classification and spatial segmentation were fused to have better tea identification. The proposed method was proved to have a satisfying result with an overall accuracy of 94.3% and Kappa coefficient of 0.92 given the only 1% training pixels of all the tea pixels. The proposed model well avoids the phenomenon of same material but different spectra, and significance of reference in practical production is expected.
Key words:Tea; Different classes; Hyperspectral image; Classification; Identification
蔡庆空,李二俊,蒋金豹,乔小军,蒋瑞波,冯海宽,刘绍堂,崔希民. 联合光谱-空间信息的短波红外高光谱图像茶叶识别模型[J]. 光谱学与光谱分析, 2019, 39(08): 2522-2527.
CAI Qing-kong, LI Er-jun, JIANG Jin-bao, QIAO Xiao-jun, JIANG Rui-bo, FENG Hai-kuan, LIU Shao-tang, CUI Xi-min. Study on the Tea Identification of Near-Infrared Hyperspectral Image Combining Spectra-Spatial Information. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(08): 2522-2527.
[1] WANG Ming-hai,LONG Jiao,ZHU Xiao-qin,et al(王铭海,龙 娇,朱晓琴,等). Modern Agricultural Science and Technology(现代农业科技),2017,(12):273.
[2] MA Jian-hong,JI Li-xia,WEI Quan-gang(马建红,姬莉霞,卫权岗). Computer Simulation(计算机仿真),2012,29(7):297.
[3] Jiang J,Qiao X,He R. Journal of Food Engineering,2016,169:284.
[4] Xiong C,Liu C,Pan W,et al. Food Chemistry,2015,176:130.
[5] YU Ying-jie,WANG Qiong-qiong,WANG Bing-yu,et al(于英杰,王琼琼,王冰玉,等). Food Science(食品科学),2014,35(22):159.
[6] LIU Fei,LI Chun-hua,GONG Xue-jiao,et al(刘 飞,李春华,龚雪蛟,等). Journal of Nuclear Agricultural Sciences(核农学报),2016,30(7):1386.
[7] CAI Jian-rong,HAN Zhi-yi(蔡健荣,韩智义). Journal of Agricultural Mechanization Research(农机化研究),2013,(4):140.
[8] Kelman T,Ren J,Marshall S. Artificial Intelligence Research,2013,2(4):87.
[9] PECIM Sisu Chemical Imaging Workstation,http://www.qd-china.com/uploads/UserUp/SisuCHEMA.pdf.
[10] Qiao X,Jiang J,Qi X,et al. Food Chemistry,2016,220:393.
[11] Richards J A. Remote Sensing Digital Image Analysis An Introduction (5th edition). Berlin:Springer Science & Business Media,2013.
[12] Kuo B C,Landgrebe D A. IEEE Transaction on Geoscience and Remote Sensing,2004,42(5):1096.
[13] Chang C I. Hyperspectral Data Exploitation: Theory and Applications. Wiley-Interscience, 2007.
[14] GAO Yun-liang, MA Ling(高运良,马 玲). Mathematical Statistics(数理统计). Beijing:Coal Industry Press(北京:煤炭工业出版社),2002.
[15] Kang X,Li S,Fang L,et al. IEEE Transactions on Geoscience and Remote Sensing,2015,53(4):2241.
[16] Shen J,Yang X,Li X,et al. IEEE Transactions on Cybernetics,2013,43(2):425.
[17] Chang C C,Lin C J. ACM Transactions on Intelligent Systems and Technology,2011,2(3):1.