Article Details

Abstract

This paper uses optical imaging technology to establish an image dataset of a batch of tobacco leaves with known nicotine content, and uses the neural network model U2-Net to accurately detect tobacco leaf targets. By extracting the color distribution information of the tobacco leaf targets, four typical Machine Learning algorithms of RF, XGBoost, MLP, and KNN are used to make the regression prediction for the nicotine content of tobacco leaves, respectively. The results indicate that the KNN model can effectively utilize color distribution information to accurately predict the nicotine content of tobacco leaves. The value of determination coefficient R2 is as high as 97.46%, the MSE is as low as 0.020 2, and the MAE is as low as 0.075 6, indicating a significant correlation between tobacco leaf color distribution information and nicotine content, and providing an effective nondestructive detection method for nicotine.

Keywords

color distribution; nicotine prediction; regression model; K-Nearest Neighbor; nondestructive testing

References

1. [1] Jiang Wei, Tang Liang, Xue Bowen, etc Research on Hyperspectral Monitoring and Prediction of Total Nitrogen and Nicotine Content in Tobacco Leaves Based on Continuous Wavelet Transform [J]. Chinese Journal of Tobacco, 2023, 29 (4): 33-43
2. [2] Wang Yuhua, Du Chuanyin, Wang Xianwei, etc The effect of box baking on the quality of tobacco leaves after baking [J]. Anhui Agricultural Science, 2024, 52 (1): 172-177
3. [3] Zhu Beibei, He Shengbao, An Hongzhen, etc Chemical composition analysis of cigar tobacco leaves for different purposes and their impact on sensory quality [J]. Anhui Agricultural Science, 2023, 51 (23): 181-184
4. [4] Leng Hongqiong, Guo Yadong, Liu Wei, etc FT-NIR spectroscopic determination of chlorogenic acid, rutin, hyoscyamine, and total polyphenol content in tobacco [J]. Spectroscopy and Spectral Analysis, 2013, 33 (7): 1801-1804
5. [5] Ge Jiong, Wang Weimiao, Zhang Jianping Rapid determination of pH value in tobacco using near-infrared spectroscopy technology [J]. Journal of Analytical Testing, 2009, 28 (6): 742-745
6. [6] Pan Wei, Ma Wenguang, Zheng Yunye, etc Non destructive determination of starch content in tobacco seeds using near-infrared spectroscopy [J]. Tobacco Science and Technology, 2017, 50 (2): 15-21
7. [7] Li Yangyang, Zhang Cihai, Peng Qianrong, etc Rapid determination of nicotine tar and carbon monoxide release in cigarette smoke by near-infrared spectroscopy [J]. Anhui Agricultural Science, 2022, 50 (17): 175-178
8. [8] Wu Xuemei, Zhang Fugui, Lv Jingtang Research on Tea Leaf Recognition Method Based on Image Color Information [J]. Tea Science, 2013, 33 (6): 584-589
9. [9] Liu Yanping, Wang Yun, Jia Zhe, etc Research on Quality Markers of Honeysuckle Based on Color Feature Component Correlation Analysis and Network Pharmacology [J]. Chinese Herbal Medicine, 2024, 55 (14): 4882-4896
10. [10] Liang Hongbo, Li Niansheng, Yuan Jian, etc The Relationship between Color and Intrinsic Quality of Tobacco Leaves [J]. China Tobacco Science, 2002 (1): 9-11
11. [11] Ding Gensheng, Zhang Qingming, Ba Jinsha, etc Analysis of the relationship between color and chromaticity indicators of tobacco leaves and the quality of tobacco leaves [J]. China Tobacco Science, 2011, 32 (4): 14-18
12. [12] Duan Yulin, Song Gang, Zhou Hongjian, etc Application of color analysis in tobacco grading [J]. Journal of Luoyang Institute of Technology: Natural Science Edition, 2013, 23 (4): 5-7
13. [13] Jiang Shuqin, Niu Huimin Research on the Application of Artificial Intelligence in Agriculture under the Background of Big Data [J]. Shanxi Agricultural Economics, 2019 (19): 77-78
14. [14] Wang Yu, Zheng Zihui The application direction and development path of artificial intelligence technology in the field of agriculture [J]. Information and Communication Technology and Policy, 2019 (6): 29-31
15. [15] Liu Shuangyin, Huang Jiande, Huang Zitao, etc Overview of the Current Status and Application of Agricultural Artificial Intelligence [J]. Modern Agricultural Equipment, 2019, 40 (6): 7-13
16. [16] Wang Fengjuan Application scenarios of artificial intelligence (AI) technology in agricultural fields such as fruits and vegetables [J]. Yantai Fruit Tree, 2019 (1): 7-8
17. [17] Liu Ping Research on the Integration of Internet, Big Data, Artificial Intelligence and Agricultural Economy [J]. Shanxi Agricultural Economy, 2019 (8): 76
18. [18] Zhang Xinheng, Li Jie, Zhou Jun, etc Research and Application of Gas Chromatography for Determination of Nicotine Content in Total Particulate Matter of Cigarette Smoke [J]. Health Research, 1991, 20 (6): 26-28+57
19. [19] QIN X B，ZHANG Z C，HUANG C Y，et al. U2-Net: Going deeper with nested U-structure for salient object detection[J/OL].Pattern Recognition，2020，106：107404[2024-10-06]. https://doi.org/10.1016/j.patcog.2020.107404。

Funding

China National Tobacco Corporation Yunnan Provincial Science and Technology Plan Project (2022530000241026)

About the authors

Xie Jiani (1997-), female, Han ethnicity, from Qujing, Yunnan, is currently pursuing a master's degree in spectral information processing; Corresponding author: Chen Zaiqing (1978-), male, Han ethnicity, from Kunming, Yunnan, professor, PhD, research direction: color vision, computer vision.