Comparison of Convolutional Neural Networks Transfer Learning Models for Disease Classification of Food Crop

Ruvita Faurina - Bengkulu University, Bengkulu, 38122, Indonesia
Silvia Rahma - Bengkulu University, Bengkulu, 38122, Indonesia
Arie Vatresia - Bengkulu University, Bengkulu, 38122, Indonesia
Agus Susanto - Bengkulu University, Bengkulu, 38122, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.4.1936

Abstract


Indonesia is an agricultural country with 29% of the workforce working in the agricultural sector, however, farmers' knowledge and practices depend on informal local wisdom based on inherited past practices. Moreover, identifying diseases in plants is difficult to do with human vision so that intelligent technology is needed.  In this paper, an architecture of CNN models such as MobileNetV2, ResNetV50, InceptionV3 and DenseNet121 will be built to detect diseases based on leaf images of several crops obtained from the agroai dataset containing multiple crops namely bean, chili, corn, potato, tomato and tea. The model is used through transfer learning for feature extraction of the trained model with imagenet weights, with 4 fully connected layers. Each model for each crop will be compared to get the best model based on the accuracy of training, evaluation and testing. ResNet50 has the best performance for four type of plants, including bean plants with training accuracy of 99.49%, validation of 99.52%, testing of 98.96%, chili plants with training accuracy of 98.03%, evaluation of 98.75%, testing of 100%, tea plants with training accuracy of 99.62%, evaluation of 99.6%, testing of 99.74% and tomato plants with training accuracy of 99.62%, validation of 99.7%, testing of 99.37%. Moreover, MobileNetV3 has the best performance for 2 types of crops that is corn with training accuracy of 99.22%, validation of 99.69%, testing of 99.55%, and potato with training accuracy of 99.62%, evaluation of 99.60%, testing of 99.74%.


Keywords


CNN; transfer learning; recognition; disease classification

Full Text:

PDF

References


world bank, “The World Bank Supports Indonesia’s Agriculture Sector to Become More Resilient and Inclusive,” world bank.

P. Schreinemachers, E. B. Simmons, and M. C. S. Wopereis, “Tapping the Economic and Nutritional Power of Vegetables,” Glob. Food Sec., vol. 16, no. September 2017, pp. 36–45, 2018, doi: 10.1016/j.gfs.2017.09.005.

R. Khairiyakh and J. H. Mulyo, “Contribution of Agricultural Sector and Sub Sectors on Indonesian Economy,” vol. 18, no. 3, pp. 150–159, 2015.

F. Hidayanti, F. Rahmah, and A. Sahro, “Mockup as Internet of Things Application for Hydroponics Plant Monitoring System,” Int. J. Adv. Sci. Technol., vol. 29, no. 5, pp. 5157–5164, 2020.

BPS, “Tanaman Pangan.”

J. Beddington, P. Webb, T. G. Benton, D. Flynn, N. M. Kelly, and S. M. Thomas, “The urgency of food system transformation is now irrefutable,” Nat. Food, 2020, doi: 10.1038/s43016-020-00161-0.

T. Ulian et al., “Unlocking Plant Resources to Support Food Security and Promote Sustainable Agriculture,” Plants People Planet, no. April, pp. 421–445, 2020, doi: 10.1002/ppp3.10145.

J. B. Ristaino, P. K. Anderson, D. P. Bebber, K. A. Brauman, and N. J. Cunniffe, “The Persistent Threat of Emerging Plant Disease Pandemics to Global Food Security,” Proc. Natl. Acad. Sci., vol. 118, no. 23, pp. 1–9, 2021, doi: 10.1073/pnas.2022239118.

S. Savary, L. Willocquet, S. J. Pethybridge, P. Esker, N. Mcroberts, and A. Nelson, “The Global Burden of Pathogens and Pests on major Food Crops,” Nat. Ecol. Evol., 2019, doi: 10.1038/s41559-018-0793-y.

P. Pamela, D. Mawejje, and M. Ugen, “Severity of Angular Leaf Spot and Rust Diseases on Common Beans in Central Uganda,” vol. 15, no. 1, pp. 63–72, 2014.

Y. Anggita et al., “Heliyon Farmers ’ knowledge and practice regarding good agricultural practices ( GAP ) on safe pesticide usage in Indonesia,” Heliyon, vol. 8, no. October 2021, p. e08708, 2022, doi: 10.1016/j.heliyon.2021.e08708.

A. P. Utomo et al., “Biosfer : Jurnal Pendidikan Biologi,” vol. 13, no. 1, pp. 14–27, 2020, doi: 10.21009/biosferjpb.v13n1.14-27.

V. Singh, N. Sharma, and S. Singh, “Artificial Intelligence in Agriculture A review of imaging techniques for plant disease detection,” Artif. Intell. Agric., vol. 4, pp. 229–242, 2020, doi: 10.1016/j.aiia.2020.10.002.

A. Haque et al., “Image-Based Identification of Maydis Leaf Blight Disease of Maize ( Zea Mays ) Using Deep Learning,” Indian J. Agric. Sci., vol. 91, no. September, pp. 1362–1367, 2021.

J. Yu, A. W. Schumann, Z. Cao, S. M. Sharpe, N. S. Boyd, and N. S. Boyd, “Weed Detection in Perennial Ryegrass With Deep Learning Convolutional Neural Network,” vol. 10, no. October, pp. 1–9, 2019, doi: 10.3389/fpls.2019.01422.

Z. Wu, Y. Chen, B. Zhao, X. Kang, and Y. Ding, “Review of Weed Detection Methods Based on Computer Vision,” pp. 1–23, 2021, doi: 10.3390/ s21113647.

B. Ding, “Cassava Leaf Disease Classification Based On CNN,” vol. 16, pp. 63–69, 2022, doi: 10.54097/hset.v16i.2363.

V. K. Shrivastava et al., “Rice Plant Disease Classification Using Transfer Learning of Deep Convolutional Neural Network,” vol. XLII, no. February, pp. 18–20, 2019, doi: 10.5194/isprs-archives-XLII-3-W6-631-2019.

A. Sagar and D. Jacob, “On Using Transfer Learning For Plant Disease Detection,” 2021, doi: 10.1101/2020.05.22.110957.

Y. Gulzar, “Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique,” 2023, doi: 10.3390/su15031906.

G. Chugh, A. Sharma, P. Choudhary, and R. Khanna, “Potato Leaf Disease Detection Using Inception V3,” pp. 1363–1366, 2020.

G. Sumalatha, J. R. Singothu, and S. K. Rao, “Transfer learning-based Plant Disease Detection,” vol. 10, doi: 10.48047/IJIEMR/V10/I03/99.

M. H. Saleem and J. Potgieter, “Plant Disease Classification : A Comparative Evaluation of Convolutional Neural Networks and Deep Learning Optimizers,” 2020.

M. Ahsan, M. A. P. Mahmud, P. K. Saha, K. D. Gupta, and Z. Siddique, “Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance,” pp. 5–9, 2021, doi: 10.3390/ technologies9030052.

J. Wang and L. Perez, “Learning”.

A. Labach and S. Valaee, “Networks”.

G. Vrbančič and V. Podgorelec, “Efficient ensemble for image-based identification of Pneumonia utilizing deep CNN and SGD with warm restarts,” Expert Syst. Appl., vol. 187, no. April 2020, p. 115834, 2022, doi: 10.1016/j.eswa.2021.115834.

D. Sarwinda, R. Hilya, A. Bustamam, and P. Anggia, “ScienceDirect ScienceDirect Deep Learning in Image Classification using Residual Network ( ResNet ) Variants for Detection of Colorectal Cancer,” Procedia Comput. Sci., vol. 179, no. 2019, pp. 423–431, 2021, doi: 10.1016/j.procs.2021.01.025.

Z. Zhang, Z. Tang, Y. Wang, H. Zhang, S. Yan, and M. Wang, “Compressed DenseNet for Lightweight Character Recognition,” pp. 1–11, doi: 10.48550/arXiv.1912.07016.

C. Wang et al., “Pulmonary Image Classification Based on Inception-v3 Transfer Learning Model,” IEEE Access, vol. 7, pp. 146533–146541, 2019, doi: 10.1109/ACCESS.2019.2946000.

M. Sandler, A. Howard, M. Zhu, and A. Zhmoginov, “MobileNetV2 : Inverted Residuals and Linear Bottlenecks,” pp. 4510–4520.

S. Widyayuningtias and P. Listio, “Performance of Deep Learning Inception Model and MobileNet Model on Gender Prediction Through Eye Image,” vol. 7, no. 4, pp. 2593–2601, 2022, doi: 10.33395/sinkron.v7i4.11887.

K. He and J. Sun, “Deep Residual Learning for Image Recognition,” pp. 1–9.

K. Deeba and B. Amutha, “WITHDRAWN : ResNet - deep neural network architecture for leaf disease classification,” no. November, p. 2021, 2021, doi: 10.1016/j.micpro.2020.103364.

S. Mohd, “Offline Signature Verification using Deep Learning Convolutional Neural ( CNN ) Architectures GoogLeNet Inception-v1 and Inception-v3,” Procedia Comput. Sci., vol. 161, pp. 475–483, 2019, doi: 10.1016/j.procs.2019.11.147.

K. E. Zhang, Y. Guo, and X. Wang, “Multiple Feature Reweight DenseNet for Image Classification,” IEEE Access, vol. 7, pp. 9872–9880, 2019, doi: 10.1109/ACCESS.2018.2890127.

R. Hakim, “agroai,” kaggle. [Online]. Available: https://www.kaggle.com/datasets/raphaelhakim/agroai

J. Lu and L. Tan, “Review on Convolutional Neural Network ( CNN ) Applied to Plant Leaf Disease Classification,” pp. 1–18, 2021, doi: 10.3390/agriculture11080707.

P. H. Richemond, “Combining Learning Rate Decay and Weight With Complexity Gradient Descent,” pp. 1–10, 2018, doi: 10.48550/arXiv.1902.02881.

F. Mohameth, C. Bingcai, and K. A. Sada, “Plant Disease Detection with Deep Learning and Feature Extraction Using Plant Village,” pp. 10–22, 2020, doi: 10.4236/jcc.2020.86002.

M. Ali, “An Accurate CT Saturation Classification Using a Fine-Tuning Strategy,” no. Dc, 2017, doi: 10.3390/en10111830.