DETECTION OF TOBACCO LEAF QUALITY USING THE YOLOv11 ALGORITHM
Main Article Content
Abstract
Accurate and efficient detection of tobacco quality is essential to identify the quality of tobacco leaves and improve farmers' tobacco yields. However, due to the high similarity between classes, significant intraclass differences and complex backgrounds among different tobacco leaves, accurately identifying tobacco quality through neural network models can pose significant challenges. To address this problem, this paper is presented with a fast and accurate method of detecting and identifying tobacco leaf quality using YOLO (You Only Look Once). This model uses YOLOv11 which incorporates an efficient detection head designed to detect the characteristics of tobacco leaves. In addition, an in-depth surveillance layer is introduced into the network along with incorporating and enhancing dynamic upsampling modules. Experimental data include public data sets of L1L, L2L, L3L, L3R, L4R, L10, L10F, and LND tobacco leaf quality. The results of the experiment showed that Yolov11 outperformed the Yolov8 and Yolov12 algorithms with a precision of 0.853, an F1 score of 0.73 [email protected], 0.811 and [email protected]:0.95 of 0.631.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
[1] L.Zhang, et al., Metabolic profiling of tobacco leaves at different growth stages or different stalk positions by gas chromatography-mass spectrometry. Ind. Crops Prod.116 (February) (2018) 46-55, doi:10.1016/j.indcrop.2018.02.041.
[2] AnonTTB, Tanzania Tobacco Board, 2023 https://www.tobaccoboard.go.tz/tobacco-growing-areas (Accessed 6 August 2023)
[3] M. Xu, J. Gao, Z.Zhang, X. Guo, Multi-channel and multi-scale separable dilated Convolutional Neural network with attention mechanism for flue-cured tobacco classification, Neural comput. Appl. 35 (21)(2023) 15511-15529, doi:10.1007/s00521-023-08544-7.
[4] M. Lu, et al., Intelligent grading of tobacco leaves using an improved bilinear convolutional neural network, IEEE Access 11 (May) (2023) 68153-68170, doi: 10.1109/ACCESS.2023.3292340.
[5] X. Xin, H. Gong, R. Hu, X. Ding, S. Pang, Y.Che. Intelligent large-scale flue-cured tobacco grading based on deep densely convolutional,Sci, Rep. 13 (1)(2023)11119, doi: 10.1038/s4 1598-023-38334-z.
[6] A. Harjoko, A. Prahara, TW. Supardi, I. Candradewi, R. Pulungan, S. Hartati, image processing approach for grading tobacco leaf based on color and quality, int, J, Smart sens, Intell syst.12 (1) (2019) 1-10, doi: 10.21307/ijsis-2019-010.
[7] K.Dormitius, Impact of Tobacco Curing on the Environment Andsocio-Economic Aspects in the Urambo District, 2021 [Online]. Available: https://dspace.nm-aist.ac.tz/handle/20.500.12479/1316.
[8] N. Mdurna, J. Leo, Dataset of banana leaves and stem images for object detection, classification and segmentation: a case of Tanzania, Data Br.49 (2023) 109322, doi:10.1016/j.dib.2023.109322.
[9] Faith Nguleni, et al., Dataset of Virginia Flue-cured Tobacco leaf images based on stalk leaf position for classification tasks: A case of Tanzania. Data in brief 56 (2024) 110817 https://doi.org/10.1016/j.dib.2024.110817.
[10] Novita Kurnia, Septian Enggar Sukmana., Classification of tobacco leaves according to the quality of single-leaf processing using backpropagation, November 2019. Symmetrical Journal of Electrical Mechanical Engineering and Computer Science 10(2): 479-486. doi: 10.24176/simet.v10i2.3066.
[11] Dwi Sri Anggun, Classification of Harvestable Tobacco Quality with Naïve Bayes Classifier, September 2022. Journal of Information Technology and Computer Engineering 3(2):46-52. doi: 10.37148/bios.v3i2.47.
[12] Iska Yanuartanti, Classification of Maturity of Virginia Tobacco Leaves Using Digital Image Processor, Journal of Electro Control (ELKON) https://doi.org/10.24176/ELKON.V3I1.10131.
[13] Sriani, Sullindawaty, Yulia Rizky, Classification of tobacco leaf quality using GLCM (Gray Level Co-occurrence Matrix) and SVM (Support Vector Machine).
[14] Nunik eka diana, Color-Based Visualization-Based Modeling Techniques for Virginia Tobacco Grading and Sorting Transparency, November 2021. Perspective 20(1):50. doi:10.21082/psp.v20n1.2021.50-62.
[15] Chunjie Zhang, Lijun Yun, Yansong Wang, Ruilin Luo, YOLO-TS: Detection Loosening Rate of Tobacco Bundles Based on YOLOv8, Januari 2024. Applied Engginering in Agriculture 40(6):623-634. Doi:10.13031/aea.16020.
[16] D. F. Putradi, B. Setiawan and A. D. W. Sumari, "Real Time Tobacco Leaf Classification Machine Using the Computer Vision with YOLO Approach on Jetson Nano," 2024 International Conference on Electrical and Information Technology (IEIT), Malang, Indonesia, 2024, pp. 19-24, doi: 10.1109/IEIT64341.2024.10763208.
[17] Yansong Wang, Chunjie Zhang, Mingjie Wu, Rullin Luo, Lin Lu, Zaiqing Chen and Lijun Yun, A Method For Detecting the rate of Tobacco leaf Loosening in Tobacco leaf sorting scenarios, frontiers in plant science, June 2025, doi: 10.3389/fpts.2025.1578317.