降维降噪处理对番茄早疫病潜育期高光谱识别效果的影响

doi:10.3964/j.issn.1000-0593(2023)03-0744-09

Abstract
References
Related Citation (15)

Download: PDF (11651 KB)
Export: BibTeX | EndNote (RIS)

Abstract Tomato early blight is highly infectious and destructive. The detection and identification of pre-symptom characteristics in the incubation period is the key to Tomato Early Blight monitoring, early warning and scientific control. In this paper, the evolution of early tomato blight was monitored by hyperspectral images, and the data were analyzed combined with visible light images and spectral characteristics. The results showed that the average value of near-infrared spectrum and red edge reflectance of tomatoes infected with early blight decreased with time, and the disease information of the incubation period appeared 36 hours after inoculation. This paper selected the spectral data of 36 h inoculation as the modeling data of Tomato Early Blight incubation period. The principal component (PCA) transformation and multivariate scattering correction (MSC) were used to reduce the spectral dimension or noise of the modeling data. Then the gradient lifting decision tree (GBDT) and support vector machine (SVM) recognition models were established, and the data were imported for training and recognition. The influence of PCA and MSC preprocessing methods on the recognition effect of gradient lifting decision tree (GBDT) and support vector machine (SVM) models is discussed. The influence of common kernel functions on SVM recognition models is further discussed, and the combination algorithm of preprocessing method and recognition model is optimized. The results showed that the accuracy of PCA-GBDT, PCA-SVM (Gaussian kernel), PCA-SVM (linear kernel), MSC-GBDT and MSC-SVM (polynomial kernel) was more than 95%, which could well realize the spectral recognition of Tomato Early Blight incubation period; Among them, MSC-GBDT has the best recognition recall and accuracy, while PCA-SVM (Gaussian kernel) has the highest recognition efficiency. The research shows that the hyperspectral data of the Tomato Early Blight incubation period after noise reduction reduces the noise is more in line with the real distribution, and has a large amount of data. The recognition ability will be insufficient, while combined with a complex recognition model, a higher test result can be achieved; The dimension reduction algorithm can reduce the dimension and amount of hyperspectral data in the incubation period of early tomato blight, and the features after dimension reduction can express the lesion information. When combined with a simple recognition model, the recognition effect is good, while with an overly complex recognition model, it will lead to over fitting the recognition model.

Key words：Tomato early blight; Incubation period; Hyperspectral imaging; Pretreatment; Support vector; Gradient lifting decision tree

Received: 2022-01-29 Accepted: 2022-07-05

ZTFLH:

O433.4

Corresponding Authors: ZHANG Yan E-mail: Eileen_zy001@sohu.com

Cite this article:

HU Zheng,ZHANG Yan. Effect of Dimensionality Reduction and Noise Reduction on Hyperspectral Recognition During Incubation Period of Tomato Early Blight[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 744-752.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2023)03-0744-09 OR https://www.gpxygpfx.com/EN/Y2023/V43/I03/744

[1] Fraser G E, Jacobsen B K, Knutsen S F, et al. Cancer Causes & Control, 2020, 31(4): 341.
[2] Dan S. International Core Journal of Engineering, 2021, 7(8): 217.
[3] Ouhami M, Hafiane A, Es-Saady Y, et al. Remote Sensing, 2021, 13(13): 2486.
[4] DANG Man-yi, MENG Qing-kui, GU Fang, et al(党满意, 孟庆魁, 谷芳, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(2): 193.
[5] Nguyen C, V Sagan, Maimaitiyiming M, et al. Sensors, 2021, 21(3): 742.
[6] Zou X, Ren Q, Cao H, et al. Journal of Information Processing Systems, 2020, 16(2): 435.
[7] ZHANG De-rong, FANG Hui, HE Yong(张德荣, 方慧, 何勇). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(6): 1748.
[8] FENG Lu, XING Fang-fang, YANG Bei-fang, et al(冯璐, 邢芳芳, 杨北方, 等). Cotton Science(棉花学报), 2020, 32(6): 569.
[9] Hashim I C, Shariff A R M, Bejo S K, et al. IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2020, 540(1): 012052.
[10] Rahman C R, Arko P S, Ali M E, et al. Biosystems Engineering, 2020, 194: 112.
[11] Barbedo J G A. Biosystems Engineering, 2019, 180: 96.
[12] LAI Jun-chen, LI Shao-kun, MING Bo, et al(赖军臣, 李少昆, 明博, 等). Scientia Agricultura Sinica(中国农业科学), 2009, 42(4): 1215.
[13] Yakkundimath R, Saunshi G, Basavaraj S. Journal of the Institution of Engineers (India): Series B, 2022, 103: 1047.
[14] Gold K M, Townsend P A, Chlus A, et al. Remote Sensing, 2020, 12(2): 286.
[15] Li X, Chen G, Liu J, et al. Chinese Geographical Science, 2017, 27(5): 827.
[16] HAN Man-li, HOU Wei-min, SUN Jing-guo, et al(韩嫚莉, 侯卫民, 孙靖国, 等). Journal of University of Electronic Science and Technology of China(电子科技大学学报), 2019, 48(1): 117.
[17] XIONG Jing-ling, ZHU Xi-cun, GAO Hua-guang, et al(熊静玲, 朱西存, 高华光, 等). Acta Pedologica Sinica(土壤学报), 2018, 55(6): 1336.
[18] ZHANG Yin-guo, TAO Yu-xiang, LUO Xiao-bo, et al(张因国, 陶于祥, 罗小波, 等). Infrared Technology(红外技术), 2020, 42(12): 1185.
[19] Zhu J, Wu A, Wang X, et al. Multimedia Tools and Applications, 2020, 79(21): 14539.
[20] LIU Li-bo, CHENG Xiao-long, DAI Jian-guo, et al(刘立波, 程晓龙, 戴建国, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017, 33(12): 201.
[21] WANG Ying-xu, SUN Ye, LI Yu-hua, et al(王迎旭, 孙晔, 李玉花, 等). Journal of Nanjing Agricultural University(南京农业大学学报), 2020, 43(4): 770.
[22] XIA Yong-quan, WANG Bing, ZHI Jun, et al(夏永泉, 王兵, 支俊, 等). Journal of Graphics(图学学报), 2018, 39(1): 57.
[23] MA Le-le, ZHAO Xin-gang, LI Zi-you, et al(马乐乐, 赵新刚, 李自由, 等). Information and Control(信息与控制), 2020, 49(1): 114.