Abstract
Cassava is one of the main sources of carbohydrates in the world. However, the diagnosis of diseases in cassava crops is laborious, time-consuming and requires specialised personnel. In addition, very little research is available on images of cassava leaves taken with mobile phones and under field conditions. Therefore, the study designs deep learning models for the detection of diseases in cassava leaves from photos taken with mobile phones in the field. This study used a dataset of 21’397 images of cassava bacterial blight, cassava brown streak disease, cassava green mottle and cassava mosaic disease from a Kaggle competition. Twelve CNN models have been evaluated by applying transfer learning and data augmentation. Each of the models was trained with uniform samples and class-weighted samples. The results showed that the use of weighted samples reduced F1 score and accuracy in all cases. Furthermore, the DenseNet169 model was outstanding with an accuracy and F1 score of 74.77% and 0.59 respectively. Finally, the causes that hinder correct classification have been identified. The results reveal that it is still necessary to work on creating a balanced and refined database.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Olsen, K.M., Schaal, B.A.: Microsatellite variation in cassava (Manihot esculenta, Euphorbiaceae) and its wild relatives: further evidence for a southern Amazonian origin of domestication. Am. J. Botany 88(1), 131–42 (2001). https://doi.org/10.2307/2657133
Gibbons, A.: New view of early amazonia: Recent findings suggest complex culture was indigenous to the Amazon basin-upsetting some received opinions about environment and culture. Science 248(4962), 1488–90 (1990). https://doi.org/10.1126/science.248.4962.1488
Patiño, V.M.: Plantas cultivadas y animales domésticos en América Equinoccial, Imprenta Departamental (1963) (in Spanish)
Wanapat, M., Kang, S.: Cassava chip (Manihot esculenta Crantz) as an energy source for ruminant feeding. Animal Nutrition. 1(4), 266–270 (2015). https://doi.org/10.1016/j.aninu.2015.12.001
Howeler, R., Lutaladio, N., Thomas, G.: Save and Grow: Cassava. A Guide to Sustainable Production Intensification. FAO (2013)
Nassar, N.M., Ortiz, R.: Cassava improvement: Challenges and impacts. J. Agricult. Sci. 145(2), 163–171 (2007). https://doi.org/10.1017/S0021859606006575
Ekeleme, F., et al.: Increasing cassava root yield on farmers’ fields in Nigeria through appropriate weed management. Crop Protection 150, 105810 (2021). https://doi.org/10.1016/j.cropro.2021.105810
Patil, B.L., Legg, J.P., Kanju, E., Fauquet, C.M.: Cassava brown streak disease: a threat to food security in Africa. J. Gen. Virol. 96(5), 956–68 (2015). https://doi.org/10.1099/jgv.0.000014
Haggag, W.M., Saber, M., Abouziena, H.F., Hoballah, E.M., Zaghloul, A.M.: Climate change potential impacts on plant diseases and their management. Der Pharm. Lettre 8(5), 17–24 (2016)
Ranjan, M., Weginwar, M.R., Joshi, N., Ingole, A.B.: Detection and classification of leaf disease using artificial neural network. Int. J. Tech. Res. Appl. 3(3), 331–3 (2015)
Kusumo, B.S., Heryana, A., Mahendra, O., Pardede, H.F.: Machine learning-based for automatic detection of corn-plant diseases using image processing. In: 2018 International Conference on Computer, Control, Informatics and Its Applications (IC3INA), pp. 93–97 (2018). https://doi.org/10.1109/IC3INA.2018.8629507
Barbedo, A., Garcia, J.: Digital image processing techniques for detecting, quantifying and classifying plant diseases. SpringerPlus 2(1), 1–12 (2013). https://doi.org/10.1186/2193-1801-2-660
Sankaran, S., Mishra, A., Ehsani, R., Davis, C.: A review of advanced techniques for detecting plant diseases. Comput. Electron. Agricult. 72(1), 1–3 (2010). https://doi.org/10.1016/j.compag.2010.02.007
Lu, J., Tan, L., Jiang, H.: Review on convolutional neural network (CNN) applied to plant leaf disease classification. Agriculture 11(8), 707 (2021). https://doi.org/10.3390/agriculture11080707
Sharma, V.K.: Designing of face recognition system. In: 2019 International Conference on Intelligent Computing and Control Systems (ICCS), 15 May 2019, pp. 459–461. IEEE (2019)
Ngugi, L.C., Abelwahab, M., Abo-Zahhad, M.: Recent advances in image processing techniques for automated leaf pest and disease recognition-A review. Inf. Process. Agricult. 8(1), 27–51 (2021). https://doi.org/10.1016/j.inpa.2020.04.004
Husin, Z.B., Shakaff, A.Y., Aziz, A.H., Farook, R.B.: Feasibility study on plant chili disease detection using image processing techniques. In: 2012 Third International Conference on Intelligent Systems Modelling and Simulation, pp. 291–296 (2012). https://doi.org/10.1109/ISMS.2012.33
Kaur, S., Pandey, S., Goel, S.: Plants disease identification and classification through leaf images: A survey. Archiv. Comput. Methods Eng. 26(2), 507–530 (2018). https://doi.org/10.1007/s11831-018-9255-6
Liu, J., Wang, X.: Plant diseases and pests detection based on deep learning: a review. Plant Methods 17(1), 1–8 (2021). https://doi.org/10.1186/s13007-021-00722-9
He, Y., Zhou, Z., Tian, L., Liu, Y., Luo, X.: Brown rice planthopper (Nilaparvata lugens Stal) detection based on deep learning. Precis. Agricult. 21(6), 1385–1402 (2020). https://doi.org/10.1007/s11119-020-09726-2
Saleem, M.H., Potgieter, J., Arif, K.M.: Plant disease detection and classification by deep learning. Plants 8(11), 468 (2019). https://doi.org/10.3390/plants8110468
Abade, A., Ferreira, P.A., de Barros, V.F.: Plant diseases recognition on images using convolutional neural networks: A systematic review. Comput. Electron. Agricult. 185, 106–125 (2021). https://doi.org/10.1016/j.compag.2021.106125
Zhang, K., Wu, Q., Liu, A., Meng, X.: Can deep learning identify tomato leaf disease? Adv. Multim. (2018). https://doi.org/10.1155/2018/6710865
Türkoğlu, M., Hanbay, D.: Plant disease and pest detection using deep learning-based features. Turkish J. Electric. Eng. Comput. Sci. 27(3): 1636–1651 (2019). https://doi.org/10.3906/elk-1809-181
Ferentinos, K.P.: Deep learning models for plant disease detection and diagnosis. Comput. Electron. Agricult. 145, 311–318 (2018). https://doi.org/10.1016/j.compag.2018.01.009
Hassan, S.M., Maji, A.K.: Plant disease identification using a novel convolutional neural network. IEEE Access 7(10), 5390–401 (2022). https://doi.org/10.1109/ACCESS.2022.3141371
Ye, Y., et al.: An improved efficientNetV2 model based on visual attention mechanism: Application to identification of cassava disease. Comput. Intell. Neurosci. 8(5) (2022). https://doi.org/10.1155/2022/1569911
Ravi, V., Acharya, V., Pham, T.D.: Attention deep learning-based large-scale learning classifier for Cassava leaf disease classification. Exp. Syst. 39(2), e12862 (2022). https://doi.org/10.1111/exsy.12862
Arivazhagan, S., Shebiah, R.N., Ananthi, S., Varthini, S.V.: Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features. Agricult. Eng. Int.: CIGR J. 15(1), 211–7 (2013)
Thangaraj, R., Anandamurugan, S., Pandiyan, P., Kaliappan, V.K.: Artificial intelligence in tomato leaf disease detection: A comprehensive review and discussion. J. Plant Diseases Protect. 1–20 (2021). https://doi.org/10.1007/s41348-021-00500-8
Mohanty, S.P., Hughes, D.P., Salathé, M.: Using deep learning for image-based plant disease detection. Front. Plant Sci. 7, 1419 (2016). https://doi.org/10.3389/fpls.2016.01419
Barbedo, J.G.: Factors influencing the use of deep learning for plant disease recognition. Biosyst. Eng. 172, 84–91 (2018). https://doi.org/10.1016/j.biosystemseng.2018.05.013
Boulent, J., Foucher, S., Théau, J., St-Charles, P.L.: Convolutional neural networks for the automatic identification of plant diseases. Front. Plant Sci. 10, 941 (2019). https://doi.org/10.3389/fpls.2019.00941
Barbedo, J.G.: A review on the main challenges in automatic plant disease identification based on visible range images. Biosyst. Eng. 144, 52–60 (2016). https://doi.org/10.1016/j.biosystemseng.2016.01.017
Shrivastava, S., Hooda, D.S.: Automatic brown spot and frog eye detection from the image captured in the field. Am. J. Intell. Syst. 4(4), 131–4 (2014). https://doi.org/10.5923/j.ajis.20140404.01
Ramcharan, A., Baranowski, K., McCloskey, P., Ahmed, B., Legg, J., Hughes, D.P.: Deep learning for image-based cassava disease detection. Front. Plant Sci. 8, 1852 (2017). https://doi.org/10.3389/fpls.2017.01852
Ramcharan, A., et al.: A mobile-based deep learning model for cassava disease diagnosis. Front. Plant Sci. 272 (2019). https://doi.org/10.3389/fpls.2019.00272
Kaggle. Cassava leaf disease classification. identify the type of disease present on a cassava leaf image (2021). https://www.kaggle.com/353competitions/cassava-leaf-disease-classification
Mwebaze, E., Gebru, T., Frome, A., Nsumba, S., Tusubira, J.: iCassava 2019 fine-grained visual categorization challenge. arXiv preprint arXiv:1908.02900 (2019).
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019). https://doi.org/10.1186/s40537-019-0197-0
Weiss, K., Khoshgoftaar, T.M., Wang, D.D.: A survey of transfer learning. J. Big Data 3(1), 1–40 (2016). https://doi.org/10.1186/s40537-016-0043-6
Smith, L.N.: Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 464–472 (2017). https://doi.org/10.1109/WACV.2017.58
Prechelt, L.: Automatic early stopping using cross validation: Quantifying the criteria. Neural Netw. 11(4), 761–7 (1998). https://doi.org/10.1016/S0893-6080(98)00010-0
Atila, Ü., Uçar, M., Akyol, K., Uçar, E.: Plant leaf disease classification using EfficientNet deep learning model. Ecol. Inf. 61, 101182 (2021). https://doi.org/10.1016/j.ecoinf.2020.101182
Tiwari, V., Joshi, R.C., Dutta, M.K.: Dense convolutional neural networks based multiclass plant disease detection and classification using leaf images. Ecol. Inf. 63, 101289 (2021). https://doi.org/10.1016/j.ecoinf.2021.101289
Acknowledgment
Thanks to the Universidad Tecnológica del Perú for its support throughout the project. The authors declare no conflict of interest related to this work. Ernesto Paiva gave the idea, did the experiments, interpreted the results and wrote the paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Paiva-Peredo, E. (2023). Deep Learning for the Classification of Cassava Leaf Diseases in Unbalanced Field Data Set. In: Woungang, I., Dhurandher, S.K., Pattanaik, K.K., Verma, A., Verma, P. (eds) Advanced Network Technologies and Intelligent Computing. ANTIC 2022. Communications in Computer and Information Science, vol 1798. Springer, Cham. https://doi.org/10.1007/978-3-031-28183-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-28183-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28182-2
Online ISBN: 978-3-031-28183-9
eBook Packages: Computer ScienceComputer Science (R0)