Authors:
Amrita,Sanjay Kumar Nayak,Rajiv Kumar,Sakshi Tomar,DOI NO:
https://doi.org/10.26782/jmcms.2020.09.00010Keywords:
Convolutional Neural Networks,Deep Learning,Plant Disease,Machine Learning,Transfer Learning,Abstract
The prime reason for human sustainability is Agriculture. With the frequent advances in technology, researchers should not forget the root and focus on improving the agriculture sector as well. A foremost challenge in the industry of agriculture is the detection of diseases in plants and its diagnosis which has gained significant attention over the past few years. Plant diseases have significantly degraded the overall food production. This is adversely affecting both the quantity and quality of products of agricultural. In this paper, several deep learning (DL) models are proposed to recognize the multiple classes of diseases present in plants from the images of leaves taken under various resolutions and different environmental conditions. Employing a Deep Convolutional Neural Network (CNN) in multi-class classification for detecting plant diseases can be beneficial in the early identification of these diseases and also in dealing with the negative impact of these diseases on agriculture. In the proposed method, five deep CNN models such as Sequential, ResNet50, InceptionV3, VGG16, and VGG19 are used. Comparative analysis of the implemented models suggested that DL helps in extracting the significant features and biomarkers related to these diseases. Based on the testing results, the VGG16 model beats other architectures in terms of training accuracy of 97.73% with validation accuracy of 88.82%.Refference:
I. Agarwal, M., S. Gupta, and K. Biswas. “A New Conv2D Model with Modified ReLU Activation Function for Identification of Disease Type and Severity in Cucumber Plant.” Sustainable Computing: Informatics and Systems, vol. 30, 2021. 10.1016/j.suscom.2020.100473.
II. Ametefe, D. S., S. S. Sarnin, D. M. Ali, A. Caliskan, I. T. Caliskan, A. A. Aliu, and D. John. “Enhancing Leaf Disease Detection Accuracy Through Synergistic Integration of Deep Transfer Learning and Multimodal Techniques.” Information Processing in Agriculture, 2024, (In Press). 10.1016/j.inpa.2024.09.006.
III. Coulibaly, S., B. Kamsu-Foguem, D. Kamissoko, and D. Traore. “Deep Neural Networks with Transfer Learning in Millet Crop Images.” Computers in Industry, vol. 108, 2019, pp. 115–120. 10.1016/j.compind.2019.02.003.
IV. Dahiya, S., T. Gulati, and D. Gupta. “Performance Analysis of Deep Learning Architectures for Plant Leaves Disease Detection.” Measurement: Sensors, vol. 24, 2022. 10.1016/j.measen.2022.100581.
V. Karki, S., J. K. Basak, N. Tamrakar, N. C. Deb, B. Paudel, J. H. Kook, M. Y. Kang, D. Y. Kang, and H. T. Kim. “Strawberry Disease Detection Using Transfer Learning of Deep Convolutional Neural Networks.” Scientia Horticulturae, vol. 332, 2024. 10.1016/j.scienta.2024.113241.
VI. Kaya, A., A. S. Keceli, C. Catal, H. Y. Yalic, H. Temujin, and B. Ticonderoga. “Analysis of Transfer Learning for Deep Neural Network Based Plant Classification Models.” Computers and Electronics in Agriculture, vol. 158, 2019, pp. 20–29. 10.1016/j.compag.2019.01.041.
VII. Loey, M., A. ElSawy, and M. Afify. “Deep Learning in Plant Diseases Detection for Agricultural Crops: A survey.” International Journal of Service Science, Management, Engineering, and Technology, vol. 11, no. 2, 2020, pp. 41–58. 10.4018/IJSSMET.2020040103.
VIII. Mishra, S., R. Sachan, and D. Rajpal. “Deep Convolutional Neural Network Based Detection System for Real-Time Corn Plant Disease Recognition.” Procedia Computer Science, vol. 167, 2020, pp. 2003–2010. 10.1016/j.procs.2020.03.236.
IX. Sajitha, P., A. Diana Andrushia, N. Anand, and M. Z. Naser. “A Review on Machine Learning and Deep Learning Image-Based Plant Disease Classification for Industrial Farming Systems.” Journal of Industrial Information Integration, vol. 38, 2024. 10.1016/j.jii.2024.100572.
X. Shewale, M. V., and R. D. Daruwala. “High Performance Deep Learning Architecture for Early Detection and Classification of Plant Leaf Disease.” Journal of Agriculture and Food Research, vol. 14, 2023. doi.org/10.1016/j.jafr.2023.100675.
XI. Srivastava, P., K. Mishra, V. Awasthi, V. K. Sahu, and P. K. Pal. “Plant Disease Detection Using Convolutional Neural Network.” International Journal of Advanced Research, vol. 9, no. 1, 2021, pp. 691–698. 10.21474/IJAR01/12346.
XII. Syarief, M., and W. Setiawan. “Convolutional Neural Network for Maize Leaf Disease Image Classification.” Telecommunication Computing Electronics and Control, vol. 18, no. 3, 2020, pp. 1376. 10.12928/telkomnika.v18i3.14840.
XIII. Too, E. C., L. Yujian, S. Njuki, and L. Yingchun. “A Comparative Study of Fine-Tuning Deep Learning Models for Plant Disease Identification.” Computers and Electronics in Agriculture, vol. 161, 2019, pp. 272–279. d10.1016/j.compag.2018.03.032.
XIV. Yousuf, A., and U. Khan. “Ensemble Classifier for Plant Disease Detection.” International Journal of Computer Science and Mobile Computing, vol. 10, no. 1, 2021, pp. 14–22. 10.47760/ijcsmc.2021.v10i01.003.
XV. https://www.keras.io
XVI. https://developer.nvidia.com/cuda-zone
XVII. DATASET: https://www.kaggle.com/datasets/emmarex/plantdisease