Convolutional Neural Network Technique for Distinguishing Nine Varieties of Vegetable Crops

Young-Yeol Cho; Ki Young Choi; Bo Hyun Sung; Nayoung Kwak

doi:10.22698/jales.20240011

All Issue

2024 Vol.36, Issue 2 Preview Page Next Page

Research Article

Convolutional Neural Network Technique for Distinguishing Nine Varieties of Vegetable Crops

30 June 2024. pp. 123-131

PDF XML

Abstract

In the field of agriculture, conducting research on neural network models for image classification is necessary to accurately categorize crops based on their types and health conditions and distinguish them from other species, to minimize crop losses. This study aimed to compare multiple neural network models to select the optimal model that can classify the images of nine vegetable seedlings, such as carrot, Kimchi cabbage, kohlrabi, lettuce, mallow, mustard, pak-choi, spinach, and sweet pepper. The best model was selected based on its accuracy (precision, recall, and F1 score) from eight trained models, namely DenseNet201, InceptionResNetV2, InceptionV3, MobileNetV2, ResNet152V2, VGG16, VGG19, and Xception. To train the models, a 9-class dataset, 20 epochs, 32 batch sizes, Adam optimizer, and a learning rate of 0.001 were used. The DenseNet201 model exhibited the highest accuracy and was, therefore, selected as the optimal model. With a batch size of 128, Adam optimizer, and a learning rate of 0.001, this model exhibited high precision, recall, and F1 score, and its superiority was confirmed using a confusion matrix. As a result, the DenseNet201 model is expected to improve the recognition performance of the model by using images of various plant species, exploring more networks, and optimizing the hyperparameters to achieve higher recognition accuracy.

Keywords

Confusion matrix

Convolutional neural network

DenseNet201

Image classification

Vegetables

References

Baek, Y. T., Sul, S. G., Cho, Y. Y. (2023) Estimation of days after transplanting using an artificial intelligence CNN(Convolutional Neural Network) model in a closed-type plant factory. Hortic Sci Technol 41:81-90. doi:10.7235/HORT.20230008

10.7235/HORT.20230008

Choi, Y. W., Kim, N. E., Paudel, B., Kim, H. T. (2022) Strawberry pests and disease detection technique optimized for symptons using deep learning algorithm. J Bio-Env Con 31:255-260. doi:10.12791/KSBEC.2022.31.3255

10.12791/KSBEC.2022.31.3.255

Elnemr, H. A. (2019) Convolutional neural network architecture for plant seedling classification. Int J Adv Comput Sci Appl 10:319-325. doi:10.14569/IJACSA.2019.0100841

10.14569/IJACSA.2019.0100841

Gupta, K., Rani, R., Bahia, N. K. (2020) Plant-seedling classification using transfer learning-based deep convolutional neural networks. Int J Agr & Environ Inform Sys 11:25-40. doi:10.4018/IJAEIS.2020100102

10.4018/IJAEIS.2020100102

Han, H. S., Kim, D. H., Chae, J. W., Lee, S. A., Kim, Y. J., Cho, H. U., Cho, H. C. (2020) A Study of tomato disease classification system based on deep learning. Trans Korean Inst Electr Eng 69:349-355. doi:10.5370/KIEE.2020.69.2.349

10.5370/KIEE.2020.69.2.349

Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K. Q. (2018) Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2261-2269. doi:10.1109/CVPR.2017.243

10.1109/CVPR.2017.243PMC5598342

Kalaivani, K. S., Kanimozhiselvi, C. S., Priyadharshini, N., Nivedhashri, S., Nandhini, R. (2022) Classification of plant seedling using deep learning techniques. In: Hemanth, D.J., Pelusi, D, Vuppalapati, C. (eds) Intelligent data communication technologies and internet of things. Lecture Notes on Data Engineering and Communications Technologies, vol. 101. Springer, Singapore. doi:10.1007/978-981-16-7610-9_76

10.1007/978-981-16-7610-9_76

Kumaratenna, K. P. S., Cho, Y. Y. (2024) Tea leaf disease classification using artificial intelligence (AI) models. J Bio-Env Con 33:1-11. doi:10.12791/KSBEC.2024.33.1.001

10.12791/KSBEC.2024.33.1.001

Milioto, A., Lottes, P., Stachniss, C. (2018) Real-time semantic segmentation of crop and weed for precision agriculture robots leveraging background knowledge in CNNs. In 2018 IEEE Intl Conf on Robotics & Automation. doi:10.48550/arXiv.1709.06764

10.1109/ICRA.2018.8460962

Moon, T. W., Park, J. Y., Son, J. E. (2020) Estimation of sweet pepper crop fresh weight with convolutional neural network. Protected Hortic Plant Fac 29:381-387. doi:10.12791/KSBEC.2020.29.4.381

10.12791/KSBEC.2020.29.4.381

Purwaningsih, T., Anjani, I. A., Utami, P. B. (2018) Convolutional neural networks implementation for chili classification. In: 2018 International Symposium on Advanced Intelligent Informatics (SAIN) 190-194. doi:10.1109/SAIN.2018.8673373

10.1109/SAIN.2018.8673373

Samiei, S., Rasti, P., Ly Vu, J., Rousseau, D. (2020) Deep learning-based detection of seedling development. Plant Methods 16:103. doi/10.1186/s13007-020-00647-9

10.1186/s13007-020-00647-932742300PMC7391498

Sandeep Kumar, K., Rajeswari, Usha, B. N. (2018) Convolution neural network based weed detection in horticulture plantation. Int J Sci Res Rev 7:41-47. doi:16.10089.IJSRR.2018.V7I06.5245.2394

Shorten, C., Khoshgoftaar, T. M. (2019) A survey on image data augmentation for deep learning. J Bio Data 6:60. doi:10.1186/s40537-019-0197-0

10.1186/s40537-019-0197-0

Xiao, Z., Tan, Y., Liu, X., Yang, S. (2019) Classification method of plug seedlings based on transfer learning. Appl Sci 9:2725. doi:10.3390/app9132725

10.3390/app9132725

Yang, B., Xu, Y. (2021) Application of deep-learning approaches in horticultural research: a review. Hortic Res 8:123. doi:10.1038/s41438-021-00560-9

10.1038/s41438-021-00560-934059657PMC8167084

Information

Publisher :Agriculture and Life Sciences Research Institute, Kangwon National University
Publisher(Ko) :강원대학교 농업생명과학대학 농업생명과학연구원
Journal Title :Journal of Agricultural, Life and Environmental Sciences
Journal Title(Ko) :농업생명환경연구
Volume : 36
No :2
Pages :123-131
Received Date : 2024-03-19
Revised Date : 2024-05-28
Accepted Date : 2024-06-03
DOI :https://doi.org/10.22698/jales.20240011

Journal of Agricultural, Life and Environmental Sciences ISSN:2233-8322(Print) 2508-870X(Online) 농업생명환경연구

All Issue