|
|
|
|
|
|
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.
|
Received: 2018-06-25
Accepted: 2018-11-06
|
|
Corresponding Authors:
JIANG Jin-bao
E-mail: jjb@cumtb.edu.cn
|
|
[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. |
[1] |
YANG Guang1, JIN Chun-bai1, REN Chun-ying2*, LIU Wen-jing1, CHEN Qiang1. Research on Band Selection of Visual Attention Mechanism for Object
Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 266-274. |
[2] |
WANG Cai-ling1,ZHANG Jing1,WANG Hong-wei2*, SONG Xiao-nan1, JI Tong3. A Hyperspectral Image Classification Model Based on Band Clustering and Multi-Scale Structure Feature Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 258-265. |
[3] |
GAO Hong-sheng1, GUO Zhi-qiang1*, ZENG Yun-liu2, DING Gang2, WANG Xiao-yao2, LI Li3. Early Classification and Detection of Kiwifruit Soft Rot Based on
Hyperspectral Image Band Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 241-249. |
[4] |
YANG Wen-feng1, LIN De-hui1, CAO Yu2, QIAN Zi-ran1, LI Shao-long1, ZHU De-hua2, LI Guo1, ZHANG Sai1. Study on LIBS Online Monitoring of Aircraft Skin Laser Layered Paint Removal Based on PCA-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3891-3898. |
[5] |
LUO Li, WANG Jing-yi, XU Zhao-jun, NA Bin*. Geographic Origin Discrimination of Wood Using NIR Spectroscopy
Combined With Machine Learning Techniques[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3372-3379. |
[6] |
DONG Jian-jiang1, TIAN Ye1, ZHANG Jian-xing2, LUAN Zhen-dong2*, DU Zeng-feng2*. Research on the Classification Method of Benthic Fauna Based on
Hyperspectral Data and Random Forest Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3015-3022. |
[7] |
JIA Zong-chao1, WANG Zi-jian1, LI Xue-ying1, 2*, QIU Hui-min1, HOU Guang-li1, FAN Ping-ping1*. Marine Sediment Particle Size Classification Based on the Fusion of
Principal Component Analysis and Continuous Projection Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3075-3080. |
[8] |
GUO Ge1, 3, 4, ZHANG Meng-ling3, 4, GONG Zhi-jie3, 4, ZHANG Shi-zhuang3, 4, WANG Xiao-yu2, 5, 6*, ZHOU Zhong-hua1*, YANG Yu2, 5, 6, XIE Guang-hui3, 4. Construction of Biomass Ash Content Model Based on Near-Infrared
Spectroscopy and Complex Sample Set Partitioning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3143-3149. |
[9] |
ZHAO Ling-yi1, 2, YANG Xi3, WEI Yi4, YANG Rui-qin1, 2*, ZHAO Qian4, ZHANG Hong-wen4, CAI Wei-ping4. SERS Detection and Efficient Identification of Heroin and Its Metabolites Based on Au/SiO2 Composite Nanosphere Array[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3150-3157. |
[10] |
ZHANG Yue1, 3, ZHOU Jun-hui1, WANG Si-man1, WANG You-you1, ZHANG Yun-hao2, ZHAO Shuai2, LIU Shu-yang2*, YANG Jian1*. Identification of Xinhui Citri Reticulatae Pericarpium of Different Aging Years Based on Visible-Near Infrared Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3286-3292. |
[11] |
WEI Zi-kai, WANG Jie, ZHANG Ruo-yu, ZHANG Meng-yun*. Classification of Foreign Matter in Cotton Using Line Scan Hyperspectral Transmittance Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3230-3238. |
[12] |
MA Qian1, 2, YANG Wan-qi1, 2, LI Fu-sheng1, 2*, CHENG Hui-zhu1, 2, ZHAO Yan-chun1, 2. Research on Classification of Heavy Metal Pb in Honeysuckle Based on XRF and Transfer Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2729-2733. |
[13] |
YANG Sen1, ZHANG Xin-ao1, XING Jian1, DAI Jing-min2. Study on Multi-Feature Model Fusion Variety Classification and Multi-Parameter Appearance Inspection for Milled Rice[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2837-2842. |
[14] |
ZHANG Fu1, 2, WANG Xin-yue1, CUI Xia-hua1, YU Huang1, CAO Wei-hua1, ZHANG Ya-kun1, XIONG Ying3, FU San-ling4*. Identification of Maize Varieties by Hyperspectral Combined With Extreme Learning Machine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2928-2934. |
[15] |
JIN Chun-bai1, YANG Guang1*, LU Shan2*, LIU Wen-jing1, LI De-jun1, ZHENG Nan1. Band Selection Method Based on Target Saliency Analysis in Spatial Domain[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2952-2959. |
|
|
|
|