Mobile Device-Based Detection System of Diseases and Pests in Rose Plants Using Deep Convolutional Neural Networks and Quantization

Year 2025, Volume: 31 Issue: 2, 302 - 318, 25.03.2025

Burhan Duman

Abstract

In agriculture, the rapid and accurate identification of plant diseases and pests is crucial for maintaining the quality and yield of agricultural products. This study focuses on detecting diseases and pests affecting Rosa damascena Mill. plants through an ensemble learning approach and deploying the model in an Android mobile application-a rarity in similar research. A new dataset was created using images from the natural habitat and season of Rosa damascena Mill., covering seven different diseases and pests. For this approach, pre-training was performed with mixed- Convolutional Neural Network (CNN) models DenseNet169, ResNet152, MobileNetV2, VGG19, and NasNet. DenseNet169 and MobileNetV2, which are the models with the highest classification success obtained from mixed-CNN models, were combined in the new model by fine- tuning with the ensemble learning method. In the performance tests of the model, an accuracy of 95.17% was obtained. In addition, this study introduces an Android mobile application integrating these models, a distinctive feature compared to other similar studies. The best performances of these models, DenseNet169 and MobileNetV2 in both flat buffered and quantized forms, were performed separately on a computer, a physical mobile device, and an Android emulator. MobileNetV2 outperformed DenseNet169 (2271 ms) by having the lowest average inference time (301 ms) on mobile devices. These results demonstrate the effectiveness of using a mobile device to detect rose plant diseases and pests efficiently in natural environments.

Keywords

Mobile aplication, Image classification, Deep learning, Plant disease and pests, Rosa damascena Mill.

Thanks

I would like to thank Assist. Prof. Sinan Demir, member of the Faculty of Agriculture, Isparta University of Applied Sciences for his support in the systematic classification of diseases and pests. I am also thankful to Kaggle and Google for supplying free GPU computation platform.

References

• Abulwafa A E (2022). A Survey of Deep Learning Algorithms and its Applications. Nile Journal of Communication and Computer Science 3(1): 28-49
• Adebisi J, Srinu S & Mitonga V (2024). Deep Learning Algorithm Analysis of Potato Disease Classification for System on Chip Implementation. Journal of Digital Food, Energy & Water Systems 5(1)
• Ahila P, Arivazhagan R S, Arun M & Mirnalini A (2019). Maize leaf disease classification using deep convolutional neural networks. Neural Comput. Appl. 31: 8887-8895
• Ahn H, Chen T, Alnaasan N, Shafi A, Abduljabbar M & Subramoni H (2023). Performance Characterization of using Quantization for DNN Inference on Edge Devices: Extended Version arXiv preprint arXiv:2303.05016
• Astani M, Hasheminejad M & Vaghefi M (2022). A diverse ensemble classifier for tomato disease recognition. Computers and Electronics in Agriculture 198: 107054
• Baydar H (2016). Oil Rose Cultivation and Industry. Science and Technology of Medicinal and Aromatic Plants (5th Expanded Edition). Süleyman Demirel University Press, 51: 290-325 (In Turkish)
• Bıtrak O O & Hatırlı S A (2022). Global Oil Rose Market and Turkey’s Role. Selçuk University Akşehir Vocational School Journal of Social Sciences 13: 85-94 (In Turkish)
• Chen J, Chen J, Zhang D, Sun Y & Nanehkaran Y A (2020). Using deep transfer learning for image-based plant disease identification. Computers and Electronics in Agriculture 173: 105393
• Chen Y, Zheng B, Zhang Z, Wang Q, Shen C & Zhang Q (2020). Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions. ACM Computing Surveys (CSUR) 53(4): 1-37
• Dewangan O (2023). Study and Innovative Approach of Deep Learning Algorithms and Architecture. In Exploring Future Opportunities of Brain-Inspired Artificial Intelligence (pp. 28-45). IGI Global
• Ersan R & Başayiğit L (2022). Ecological modelling of potential Isparta Rosa areas (Rosa damascena Mill.). Industrial Crops and Products 176: 114427
• Fazili M A, Ganie I B & Hassan Q P (2024). Studies on pharmacological aspects, integrated pest management and economic importance of Rosa damascena L. South African Journal of Botany 174: 534-541
• Ferentinos K P (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture 145: 311-318
• Fuentes A F, Yoon S, Lee J & Park D S (2018). High-performance deep neural network-based tomato plant diseases and pests diagnosis system with refinement filter bank. Frontiers in Plant Science 9: 1162
• Gholami A, Kim S, Dong Z, Yao Z, Mahoney M W & Keutzer K (2022). A survey of quantization methods for efficient neural network inference. In Low-Power Computer Vision (pp. 291-326). Chapman and Hall/CRC
• Harbola G, Rawat M S, Gupta A & Gupta R (2024, May). Intelligent Diagnosis of Potato Leaf Diseases using Deep Learning. In 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN) 372-377 IEEE
• Hemalatha N K, Brunda R N, Prakruthi G S, Prabhu B V B, Shukla A & Narasipura O S J (2022). Sugarcane leaf disease detection through deep learning. In Deep Learning for Sustainable Agriculture, 297-323 https://doi.org/10.1016/B978-0-323-85214-2.00003-3
• Huang G, Liu Z, Van Der Maaten L & Weinberger K Q (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700-4708
• Iman M, Arabnia H R & Rasheed K (2023). A review of deep transfer learning and recent advancements. Technologies 11(2): 40
• Jung K, Lee J I, Kim N, Oh S & Seo D W (2021). Classification of space objects by using deep learning with micro-Doppler signature images. Sensors 21(13): 4365
• Karanfil A (2021). Prevalence and molecular characterization of Turkish isolates of the rose viruses. Crop Protection 143: 105565
• Katumba A, Okello W S, Murindanyi S, Nakatumba-Nabende J, Bomera M, Mugalu B W & Acur A (2024). Leveraging edge computing and deep learning for the real-time identification of bean plant pathologies. Smart Agricultural Technology 9: 100627. https://doi.org/10.1016/j.atech.2024.100627
• Khaleel M I, Sai P G, Kumar A U R, Raja P & Hoang V T (2022). Rose Plant Leaves: Disease Detection and Pesticide Management using CNN. 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI), 1067-1072
• Khitthuk C, Srikaew A, Attakitmongcol K & Kumsawat P (2018). Plant leaf disease diagnosis from color imagery using co-occurrence matrix and artificial intelligence system. 2018 International Electrical Engineering Congress (IEECON), 1-4
• Lee S H (2020). Deep learning based face mask recognition for access control. Journal of the Korea Academia-Industrial Cooperation Society 21(8): 395-400
• Liu Y, Sun Y, Xue B, Zhang M, Yen G G & Tan, K C (2021). A survey on evolutionary neural architecture search. IEEE Transactions on Neural Networks and Learning Systems. Ma J, Pang L, Yan L & Xiao J (2020). Detection of black spot of rose based on hyperspectral imaging and convolutional neural network. AgriEngineering 2(4): 556-567
• Mahlein AK (2016). Plant disease detection by imaging sensors–parallels and specific demands for precision agriculture and plant phenotyping. Plant Disease 100(2): 241-251
• Mutka A M & Bart R S (2015). Image-based phenotyping of plant disease symptoms. Frontiers in Plant Science 5: 734
• Nuanmeesri S (2021). A hybrid deep learning and optimized machine learning approach for rose leaf disease classification. Eng. Technol. Appl. Sci. Res. 11(5): 7678-7683
• Oikonomidis A, Catal C & Kassahun A (2023). Deep learning for crop yield prediction: a systematic literature review. New Zealand Journal of Crop and Horticultural Science 51(1): 1-26
• Pan W, Qin J, Xiang X, Wu Y, Tan Y & Xiang L (2019). A smart mobile diagnosis system for citrus diseases based on densely connected convolutional networks. IEEE Access 7: 87534-87542
• Prathiksha B J, Kumar V, Krishnamoorthi M, Poovizhi P, Sowmiya D & Thrishaa, B. (2024, April). Early Accurate Identification of Grape leaf Disease Detection using CNN based VGG-19 model. In 2024 International Conference on Cognitive Robotics and Intelligent Systems (ICC-ROBINS) (pp. 263-269). IEEE
• Rajbongshi A, Sarker T, Ahamad M M & Rahman M M (2020). Rose diseases recognition using MobileNet. 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) 1-7
• Rakib A F, Rahman R, Razi A A & Hasan A T (2024). A lightweight quantized CNN model for plant disease recognition. Arabian Journal for Science and Engineering 49(3): 4097-4108
• Reddy D S, Rajalakshmi P & Mateen M A (2021). A deep learning based approach for classification of abdominal organs using ultrasound images. Biocybernetics and Biomedical Engineering 41(2): 779-791
• Sagi O & Rokach L (2018). Ensemble learning: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 8(4): e1249
• Sethy P K, Barpanda N K, Rath A K & Behera S K (2020). Deep feature based rice leaf disease identification using support vector machine. Computers and Electronics in Agriculture 175: 105527
• Sharma R & Singh G (2015). Access to modern agricultural technologies and farmer household welfare: Evidence from India. Millennial Asia 6(1): 19-43
• Simonyan K & Zisserman A (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
• Swetharani K & Prasad G V (2021). Design and implementation of an efficient rose leaf disease detection and classification using convolutional neural network. International Journal of Image Mining 4(1): 98-113
• Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V & Rabinovich A (2015). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1-9
• Tao W, Al-Amin M, Chen H, Leu M C, Yin Z & Qin R (2020). Real-time assembly operation recognition with fog computing and transfer learning for human-centered intelligent manufacturing. Procedia Manufacturing 48: 926-931
• Uğuz S & Uysal N (2021). Classification of olive leaf diseases using deep convolutional neural networks. Neural Comput. & Applic. 33: 4133– 4149.https://doi.org/10.1007/s00521-020-05235-5
• Vallabhajosyula S, Sistla V & Kolli V K K (2022). Transfer learning-based deep ensemble neural network for plant leaf disease detection. J. Plant Dis. Prot. 129: 545-558. https://doi.org/10.1007/s41348-021-00465-8
• Vrbančič G & Podgorelec V (2020). Transfer learning with adaptive fine-tuning. IEEE Access 8: 196197-196211
• Wang C, Du P, Wu H, Li J, Zhao C & Zhu H (2021). A cucumber leaf disease severity classification method based on the fusion of DeepLabV3+ and U-Net. Computers and Electronics in Agriculture 189: 106373
• Weerakoon W M W et al. (2017). Effect of leaf color chart based nitrogen management on the performance of rice crop. Field Crops Research 151: 15-23
• Yang Y, Lv H & Chen N (2023). A survey on ensemble learning under the era of deep learning. Artificial Intelligence Review 56(6): 5545- 5589
• Yilmaz H (2015). Estimating the economic costs and level of pesticide use in oil rose (Rosa damascena Mill.) orchards: evidence from a survey for the lakes region of Turkey. Erwerbs-obstbau 57(4): 195-202
• Yin J, Yu D, Li Z, Guo W & Zhu H (2021). Chinese Rose flower disease recognition method based on deep learning. Frontier Computing: Proceedings of FC 2020, 1309-1319
• Yu Z, Wang K, Wan Z, Xie S & Lv Z (2023). Popular deep learning algorithms for disease prediction: a review. Cluster Computing 26(2): 1231-1251
• Zhong Y & Zhao M (2020). Research on deep learning in apple leaf disease recognition. Computers and Electronics in Agriculture 168: 105146
• Zoph B & Le Q V (2016). Neural architecture search with reinforcement learning. ArXiv Preprint, ArXiv:1611.01578