Convolutional Neural Network-Based Image Classification of Bacterial Wilt Symptoms in Pepper (Capsicum annuum L.)

Junesung Lee; Yena Kim; Ji-Su Kwon; Seon-In Yeom; Won-Hee Kang

doi:10.7235/HORT.20260022

Online First

Preview Page

Research Article

Convolutional Neural Network-Based Image Classification of Bacterial Wilt Symptoms in Pepper (Capsicum annuum L.)

PDF XML

Abstract

Bacterial wilt, caused by Ralstonia solanacearum, is a destructive disease that affects pepper and other solanaceous crops. Reliable phenotypic evaluations are essential for resistance screening, but conventional visual scoring can be affected by observer-dependent variations. In this study, we developed an image classification framework based on a convolutional neural network (CNN) for objective assessments of bacterial wilt symptoms in pepper. Three pepper genotypes representing resistant (MC4), moderately resistant (ECW30R), and susceptible (Subicho) responses were inoculated with R. solanacearum SL1931, after which symptom development was evaluated using a five-level disease index. Under standardized imaging conditions, 1,500 multi-view symptom images were acquired and assigned to three symptom-associated resistance classes. To reduce information leakage, images obtained from the same plant individual were assigned to the same dataset partition. The model was trained using the training set, monitored with the validation set, and evaluated using an independent test set. The final model correctly classified 266 of 300 test images, corresponding to an accuracy rate of 88.67%. Misclassifications occurred mainly between adjacent symptom classes, suggesting partial visual overlap between intermediate and severe wilt responses. These results indicate that the CNN-based image analysis method developed here can support objective and reproducible bacterial wilt phenotyping in pepper. Further validation across broader germplasm, pathogen isolates, and imaging environments will be required for large-scale breeding applications.

Keywords

digital phenotyping

disease resistance screening

image-based phenotyping

machine learning

plant disease detection

Ralstonia solanacearum

References

Barbedo JGA (2018) Factors influencing the use of deep learning for plant disease recognition. Biosyst Eng 172:84-91. https://doi.org/10.1016/j.biosystemseng.2018.05.013

10.1016/j.biosystemseng.2018.05.013

Barbedo JGA (2019) Plant disease identification from individual lesions and spots using deep learning. Biosyst Eng 180:96-107. https://doi.org/10.1016/j.biosystemseng.2019.02.002

10.1016/j.biosystemseng.2019.02.002

Bock C, Poole G, Parker P, Gottwald T (2010) Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging. CRC Crit Rev Plant Sci 29:59-107. https://doi.org/10.1080/07352681003617285

10.1080/07352681003617285

Champoiseau PG, Jones JB, Allen C (2009) Ralstonia solanacearum race 3 biovar 2 causes tropical losses and temperate anxieties. Plant Health Prog 10:35. https://doi.org/10.1094/PHP-2009-0313-01-RV

10.1094/PHP-2009-0313-01-RV

Cobb JN, DeClerck G, Greenberg A, Clark R, McCouch S (2013) Next-generation phenotyping: requirements and strategies for enhancing our understanding of genotype–phenotype relationships and its relevance to crop improvement. Theor Appl Genet 126:867-887. https://doi.org/10.1007/s00122-013-2066-0

10.1007/s00122-013-2066-023471459PMC3607725

Fahlgren N, Feldman M, Gehan MA, Wilson MS, Shyu C, Bryant DW, Hill ST, McEntee CJ, Warnasooriya SN, et al. (2015) A versatile phenotyping system and analytics platform reveals diverse temporal responses to water availability in Setaria. Mol Plant 8:1520-1535. https://doi.org/10.1016/j.molp.2015.06.005

10.1016/j.molp.2015.06.005

Genin S (2010) Molecular traits controlling host range and adaptation to plants in Ralstonia solanacearum. New Phytologist 187:920-928. https://doi.org/10.1111/j.1469-8137.2010.03397.x

10.1111/j.1469-8137.2010.03397.x

Géron A (2022) Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly Media, Inc., Sebastopol, USA

Hamet P, Tremblay J (2017) Artificial intelligence in medicine. Metab 69:S36-S40. https://doi.org/10.1016/j.metabol.2017.01.011

10.1016/j.metabol.2017.01.011

Harfouche AL, Jacobson DA, Kainer D, Romero JC, Harfouche AH, Mugnozza GS, Moshelion M, Tuskan GA, Keurentjes JJB, et al. (2019) Accelerating climate resilient plant breeding by applying next-generation artificial intelligence. Trends Biotechnol 37:1217-1235. https://doi.org/10.1016/j.tibtech.2019.05.007

10.1016/j.tibtech.2019.05.007

Huet G (2014) Breeding for resistances to Ralstonia solanacearum. Front Plant Sci 5:715. https://doi.org/10.3389/fpls.2014.00715

10.3389/fpls.2014.0071525566289PMC4264415

Jannat M, Uddin MS, Hasan MA, Alam MS, Paul A, Chowdhury MEH, Haider J (2025) Real-time jute leaf disease classification using an explainable lightweight CNN via a supervised and semi-supervised self-training approach. Front Plant Sci 16. https://doi.org/10.3389/fpls.2025.1647177

10.3389/fpls.2025.164717741210703PMC12592198

Jiang GF, Wei Z, Xu J, Chen HL, Zhang Y, She XM, Macho AP, Ding W, Liao BS (2017) Bacterial wilt in china: history, current status, and future perspectives. Front Plant Sci 8:1549. https://doi.org/10.3389/fpls.2017.01549

10.3389/fpls.2017.0154928955350PMC5601990

Kapoor S, Narayanan A (2023) Leakage and the reproducibility crisis in machine-learning-based science. Patterns 4:100804. https://doi.org/10.1016/j.patter.2023.100804

10.1016/j.patter.2023.10080437720327PMC10499856

Kim CH, Samsuzzaman MNR, Ali K, Chung SO, Kabir MSN (2023) Deep learning based identification of Pepper (Capsicum annuum L.) diseases: a review. Precis Agric 5:68. https://doi.org/10.12972/pastj.20230006

10.12972/pastj.20230006

Kwon JS, Nam JY, Yeom SI, Kang WH (2021) Leaf-to-whole plant spread bioassay for pepper and Ralstonia solanacearum interaction determines inheritance of resistance to bacterial wilt for further breeding. Int J Mol Sci 22:2279. https://doi.org/10.3390/ijms22052279

10.3390/ijms2205227933668965PMC7956186

Lee HJ, Jo EJ, Kim NH, Chae Y, Lee SW (2011) Disease responses of tomato pure lines against Ralstonia solanacearum strains from Korea and susceptibility at high temperature. Res Plant Dis 17:326-330. https://doi.org/10.5423/RPD.2011.17.3.326

10.5423/RPD.2011.17.3.326

Lee SM, Kwak YS, Lee KH, Kim HT (2015) Control efficacy of fungicides on pepper bacterial wilt. Korean J Pestic Sci 19:323-328. https://doi.org/10.7585/kjps.2015.19.3.323

10.7585/kjps.2015.19.3.323

Li LL, Zhang SJ, Wang B (2021) Plant disease detection and classification by deep learning-a review. IEEE Access 9:56683-56698. https://doi.org/10.1109/ACCESS.2021.3069646

10.1109/ACCESS.2021.3069646

Mahlein AK (2016) Plant disease detection by imaging sensors–parallels and specific demands for precision agriculture and plant phenotyping. Plant Dis 100:241-251. https://doi.org/10.1094/PDIS-03-15-0340-FE

10.1094/PDIS-03-15-0340-FE

Mohanty SP, Hughes DP, Salathé M (2016) Using deep learning for image-based plant disease detection. Front Plant Sci 7. https://doi.org/10.3389/fpls.2016.01419

10.3389/fpls.2016.0141927713752PMC5032846

Too EC, Yujian L, Njuki S, Yingchun L (2019) A comparative study of fine-tuning deep learning models for plant disease identification. Comput Electron Agric 161:272-279. https://doi.org/10.1016/j.compag.2018.03.032

10.1016/j.compag.2018.03.032

Yang W, Feng H, Zhang X, Zhang J, Doonan JH, Batchelor WD, Xiong L, Yan J (2020) Crop phenomics and high-throughput phenotyping: past decades, current challenges, and future perspectives. Mol Plant 13:187-214. https://doi.org/10.1016/j.molp.2020.01.008

10.1016/j.molp.2020.01.008

Information

Publisher :KOREAN SOCIETY FOR HORTICULTURAL SCIENCE
Publisher(Ko) :한국원예학회
Journal Title :Horticultural Science and Technology
Journal Title(Ko) :원예과학기술지
Received Date : 2026-06-06
Accepted Date : 2026-06-23
DOI :https://doi.org/10.7235/HORT.20260022

Horticultural Science and Technology 원예과학기술지 ISSN:1226-8763(Print) 2465-8588(Online)

Online First