Keywords
Deep learning
Computer vision
Disease prediction
Decision support system
How to Cite
Abstract
Cucumber is one of the major crops in Indian agrarian society, and it is affected by various diseases such as Downy Mildew. Monitoring the crop field's condition might help evade the disease, which is costly and time-consuming. Therefore, an economically intelligent farming system requires for disease monitoring. The grading of the disease can be recognized depending on the distribution of chlorophyll content in a leaf. However, previous grading techniques lead to an erroneous framework due to the inequitable statistics of real-time images' healthy and unhealthy pixel ordination. Hence, an optimized Deep Learning (DL) model is proposed according to the grading of the disease. The proposed DL model provides a training accuracy of 94.82% and a validation accuracy of 84.15%. The model also tested over 300 leaves with different grades of diseases captured randomly in an uncontrolled environment, and was found to be 90% accurate, compared to over 69% by visual identification of experts. A decision support system built on the proposed technology's instantaneous image capture and prediction capabilities is a huge help to farmers and agriculturists in understanding the state of the field and responding to such circumstances.
References
Yang X, Li M, Zhao C, Zhang Z, Hou Y. Early warning model for cucumber downy mildew in unheated greenhouses. N Z J Agric Res. 2007; 50(5): 1261-8. https://doi.org/10.1080/00288230709510411
Weizheng S, Yachun W, Zhanliang C, Hongda W. Grading method of leaf spot disease based on image processing. In: 2008 Int Conf Comput Sci Softw Eng. 2008; 6: 491-4. https://doi.org/10.1109/CSSE.2008.1649
Cen ZX, Li BJ, Shi YX, Huang HY, Liu J, Liao NF, et al. Discrimination of cucumber anthracnose and cucumber brown speck based on color image statistical characteristics. Acta Hortic Sin. 2007; 34(6): 1425-30.
Arief MA, Kim H, Kurniawan H, Nugroho AP, Kim T, Cho BK. Chlorophyll fluorescence imaging for early detection of drought and heat stress in strawberry plants. Plants. 2023; 12(6): 1387. https://doi.org/10.3390/plants12061387
Faqeerzada MA, Park E, Kim T, Kim MS, Baek I, Joshi R, et al. Fluorescence hyperspectral imaging for early diagnosis of heat-stressed ginseng plants. Appl Sci. 2022; 13(1): 31. https://doi.org/10.3390/app13010031
Mukherjee K, Das S, Mustafi S, Dan S, Mandal SN. IGDM: Image-based grading system of downy mildew in cucumber using digital image processing and unsupervised learning. J Inst Eng (India) Ser B. 2024; 105(4): 825-39. https://doi.org/10.1007/s40031-024-01005-2
Mandal SN, Mukherjee K, Dan S, Ghosh P, Das S, Mustafi S, et al. Image-based potato phoma blight severity analysis through deep learning. J Inst Eng (India) Ser B. 2023; 104(1): 181-92. https://doi.org/10.1007/s40031-022-00820-9
Masood R, Khan SA, Khan MN. Plants disease segmentation using image processing. Int J Mod Educ Comput Sci. 2016; 8(1): 24-8. https://doi.org/10.5815/ijmecs.2016.01.04
Ramanjot, Mittal U, Wadhawan A, Singla J, Jhanjhi NZ, Ghoniem RM, et al. Plant disease detection and classification: a systematic literature review. Sensors. 2023; 23(10): 4769. https://doi.org/10.3390/s23104769
Sladojevic S, Arsenovic M, Anderla A, Culibrk D, Stefanovic D. Deep neural networks based recognition of plant diseases by leaf image classification. Comput Intell Neurosci. 2016; 2016: 3289801. https://doi.org/10.1155/2016/3289801
Mohanty SP, Hughes DP, Salathé M. Using deep learning for image-based plant disease detection. Front Plant Sci. 2016; 7: 215232. https://doi.org/10.3389/fpls.2016.01419
Putra BT, Amirudin R, Marhaenanto B. Evaluation of deep learning using convolutional neural network approach for identifying Arabica and Robusta coffee plants. J Biosyst Eng. 2022; 47(2): 118–29. https://doi.org/10.1007/s42853-022-00136-y
Jeong S, Jeong S, Bong J. Detection of tomato leaf miner using deep neural network. Sensors. 2022; 22(24): 9959. https://doi.org/10.3390/s22249959
Tran TT, Choi JW, Le TT, Kim JW. Comparative study of deep CNN in forecasting and classifying the macronutrient deficiencies on development of tomato plant. Appl Sci. 2019; 9(8): 1601. https://doi.org/10.3390/app9081601
Camargo A, Smith JS. Image pattern classification for identification of disease-causing agents in plants. Comput Electron Agric. 2009; 66(2): 121-5. https://doi.org/10.1016/j.compag.2009.01.003
Aladhadh S, Habib S, Islam M, Aloraini M, Aladhadh M, Al-Rawashdeh HS. Efficient pest detection framework with a medium-scale benchmark to increase agricultural productivity. Sensors. 2022; 22(24): 9749. https://doi.org/10.3390/s22249749
Amara J, Bouaziz B, Algergawy A. Deep learning-based approach for banana leaf diseases classification. In: Datenbanksysteme für Business, Technologie und Web (BTW 2017) Workshopband. Gesellschaft für Informatik eV; 2017. p. 79-88.
Das S, Bikram P, Biswas A, Sinha P. Multilayer optimized deep learning model to analyze spectral indices for predicting condition of rice blast disease. Remote Sens Appl Soc Environ. 2025; 37: 101394. https://doi.org/10.1016/j.rsase.2024.101394
Zhou B, Xu J, Zhao J, Li A, Xia Q. Research on cucumber downy mildew detection system based on SVM classification algorithm. In: 3rd Int Conf Mater Mech Manuf Eng (IC3ME). 2015; pp. 1681-4. https://doi.org/10.2991/ic3me-15.2015.324
Gikunda PK, Jouandeau N. State-of-the-art convolutional neural networks for smart farms: a review. In: Intelligent Comput Proc Comput Conf. 2019; pp. 763-75. https://doi.org/10.1007/978-3-030-22871-2_53
Kalaivani S, Tharini C, Viswa TS, Sara KF, Abinaya ST. ResNet-based classification for leaf disease detection. J Inst Eng (India) Ser B. 2025; 106(1): 1-4. https://doi.org/10.1007/s40031-024-01062-7
Cohen B, Edan Y, Levi A, Alchanatis V. Early detection of grapevine (Vitis vinifera) downy mildew (Peronospora) and diurnal variations using thermal imaging. Sensors. 2022; 22(9): 3585. https://doi.org/10.3390/s22093585
Liu E, Gold KM, Combs D, Cadle-Davidson L, Jiang Y. Deep learning-based autonomous downy mildew detection and severity estimation in vineyards. In: ASABE Annu Int Virtual Meet. 2021; pp. 1-8. https://doi.org/10.13031/aim.202100486
Lin K, Gong L, Huang Y, Liu C, Pan J. Deep learning-based segmentation and quantification of cucumber powdery mildew using convolutional neural network. Front Plant Sci. 2019; 10: 155. https://doi.org/10.3389/fpls.2019.00155
Chen M, Brun F, Raynal M, Makowski D. Forecasting severe grape downy mildew attacks using machine learning. PLoS One. 2020; 15(3): e0230254. https://doi.org/10.1371/journal.pone.0230254
Ojiambo PS, Paul PA, Holmes GJ. Quantitative review of fungicide efficacy for managing downy mildew in cucurbits. Phytopathology. 2010; 100(10): 1066-76. https://doi.org/10.1094/PHYTO-12-09-0348
Mebrate SA, Dehne HW, Pillen K, Oerke EC. Molecular diversity in Puccinia triticina isolates from Ethiopia and Germany. J Phytopathol. 2006; 154(11-12): 701-10. https://doi.org/10.1111/j.1439-0434.2006.01177.x
Ngugi LC, Abelwahab M, Abo-Zahhad M. Recent advances in image processing techniques for automated leaf pest and disease recognition: a review. Inf Process Agric. 2021; 8(1): 27-51. https://doi.org/10.1016/j.inpa.2020.04.004
Cruz AC, Luvisi A, De Bellis L, Ampatzidis Y. X-FIDO: an effective application for detecting olive quick decline syndrome with deep learning and data fusion. Front Plant Sci. 2017; 8: 1741. https://doi.org/10.3389/fpls.2017.01741
Nikhitha M, Sri SR, Maheswari BU. Fruit recognition and grade of disease detection using inception v3 model. In: 3rd Int Conf Electron Commun Aerosp Technol (ICECA). 2019; pp. 1040-3. https://doi.org/10.1109/ICECA.2019.8822095
Chandra NM, Reddy KA, Sushanth G, Sujatha S. Versatile approach based on convolutional neural networks for early identification of diseases in tomato plants. Int J Wavelets Multiresol Inf Process. 2022; 20(1): 2150043. https://doi.org/10.1142/S0219691321500430
Kumar A, Razi R, Singh A, Das H. Res-VGG: a novel model for plant disease detection by fusing VGG16 and ResNet models. In: Int Conf Mach Learn Image Process Netw Secur Data Sci. 2020; pp. 383-400. https://doi.org/10.1007/978-981-15-6318-8_32
Ishii H, Fraaije BA, Sugiyama T, Noguchi K, Nishimura K, Takeda T, et al. Occurrence and molecular characterization of strobilurin resistance in cucumber powdery mildew and downy mildew. Phytopathology. 2001; 91(12): 1166-71. https://doi.org/10.1094/PHYTO.2001.91.12.1166
Pujari JD, Yakkundimath R, Byadgi AS. Image processing-based detection of fungal diseases in plants. Procedia Comput Sci. 2015; 46: 1802-8. https://doi.org/10.1016/j.procs.2015.02.137
Sibiya M, Sumbwanyambe M. Algorithm for severity estimation of plant leaf diseases using colour threshold image segmentation and fuzzy logic inference. AgriEngineering. 2019; 1(2): 15. https://doi.org/10.3390/agriengineering1020015
Pawar P, Turkar V, Patil P. Cucumber disease detection using artificial neural network. In: Int Conf Invent Comput Technol (ICICT). 2016; 3: pp. 1-5. https://doi.org/10.1109/INVENTIVE.2016.7830151
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Shubhajyoti Das, Subhranil Mustafi, Sanket Dan, Satyendra N. Mandal, Parimal Sinha