Detection of Bacterial Speck Disease (Pseudomonas syringae pv. tomato) in Tomato Plants Grown in Greenhouses Using Image Processing

Year 2025, Volume: 8 Issue: 6, 1895 - 1903, 15.11.2025

İsmail Öztürk , Bahadır Demirel , Sümer Horuz , Gürkan A. K. Gürdil

https://doi.org/10.34248/bsengineering.1707394

Abstract

The quality and productivity of tomatoes depend on careful monitoring and timely interventions during cultivation. This study aims to determine the level of necrosis caused by bacterial speck disease (Pseudomonas syringae pv. tomato, Pst) on tomato leaves using image processing techniques. Stake tomato seedlings were used in greenhouse experiments. After spraying the pathogenic bacteria on the leaves, they were kept at 25–27 °C and 70–80% humidity until typical disease symptoms such as chlorosis and necrosis appeared. Disease diagnosis was initially conducted using OpenCV, a Python library capable of image processing and computer vision tasks. Based on the analysis of leaf images, disease severity and observation intervals were determined. Disease percentages were identified as follows: Scale 0 at 0.00%, Scale 1 at 8.64%, Scale 2 at 24.94%, Scale 3 at 27.78%, Scale 4 at 62.97%, and Scale 5 at 89.69%. It was observed that as disease detection rates increased, accuracy rates also rose, and standard deviation decreased. Although a slight increase was observed at Scale 3 due to environmental variation, the standard deviation decreased from 0.02695 at Scale 1 to 0.02131 at Scale 5. The algorithms used accurately detected bacterial specks as disease severity increased, reducing overall variability. The results of the greenhouse study suggest that early disease detection can mitigate product losses when applied in similar environments.

Keywords

Leaf lesion quantification , Non-destructive diagnosis , Image-based plant pathology , Symptom severity assessment , Agricultural visual analytics

Ethical Statement

Ethics committee approval was not required for this study because there was no study on animals or humans.

Supporting Institution

Erciyes University Scientific Research Projects Unit

Project Number

FYL-2022-11958

Thanks

This Project was funded by the Erciyes University, Scientific Research Projects Coordination Unit, under the Project code FYL–2022–11958.

References

• Adem K, Ozguven MM, Altas Z. 2022. A sugar beet leaf disease classification method based on image processing and deep learning. Multimed Tools Appl, 82: 12577-12594.
• Altman DG, Bland JM. 1983. Measurement in medicine: the analysis of method comparison studies. Statistician, 32(3): 307-317.
• Barbedo JGA. 2018. Factors influencing the use of deep learning for plant disease recognition. Biosyst Eng, 172: 84-91.
• Barbedo JGA. 2019. Plant disease identification from individual lesions and specks using deep learning. Biosyst Eng, 180: 96-107.
• Bock CH, Poole GH, Parker PE, Gottwald TR. 2010. Plant disease severity is estimated visually, by digital photography and image analysis, and by hyperspectral imaging. Crit Rev Plant Sci, 29(2): 59-107.
• Colvine S, Branthôme FX. 2016. The tomato: a seasoned traveller. In: Causse M, Giovannoni J, Bouzayen M, Zouine M, editors. The tomato genome. Springer, Berlin, Germany, pp: 1-5.
• Ertürk YE, Çirka M. 2015. Tomato production and marketing in Turkey and Northeast Anatolia Region (NEAR). YYU J Agric Sci, 20(3): 214-221.
• Ferentinos KP. 2018. Deep learning models for plant disease detection and diagnosis. Comput Electron Agric, 145: 311-318.
• Fuentes A, Yoon S, Kim SC, Park DS. 2017. A robust deep-learning-based detector for real-time tomato plant diseases and pests’ recognition. Sensors, 17(9): 2022.
• Giavarina D. 2015. Understanding Bland-Altman analysis. Biochem Med, 25(2): 141-151.
• Haridasan A, Thomas J, Raj ED. 2023. Deep learning system for paddy plant disease detection and classification. Environ Monit Assess, 195: 120.
• Harvey M, Quilley S, Beynon H. 2002. Exploring tomatoes: transformations of nature, society and economy. Edward Elgar Publishing, Cheltenham, UK, pp: 1-250.
• Hong H, Lin J, Huang F. 2020. Tomato disease detection and classification by deep learning. In: Proceedings of the 2020 International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Fuzhou, China, pp: 25-29.
• Jones JB, Jones JP, Stall RE, Zitter TA. 1991. Compendium of tomato diseases. APS Press, St. Paul, MN, US, pp: 1-3.
• Kaur N, Devendran V. 2023. A novel framework for semi-automated system for grape leaf disease detection. Multimed Tools Appl, 83: 50733-50755.
• Keskin AH, Karakayacı Z. 2014. Evaluation of socio-economic effects of tomato moth (Tuta absoluta) on tomato production in Çumra district of Konya province. In: Proceedings of the XI National Agricultural Economics Congress, 3-5 September, Samsun, Türkiye, pp: 688-692.
• Landis JR, Koch GG. 1977. The measurement of observer agreement for categorical data. Biometrics, 33(1): 159-174.
• Mahlein AK. 2016. Plant disease detection by imaging sensors-parallels and specific demands for precision agriculture and plant phenotyping. Plant Dis, 100(2): 241-251.
• Mehta S, Kukreja V, Vats S. 2023. Advancing agricultural practices: federated learning-based CNN for mango leaf disease detection. In: Proceedings of the 2023 3rd International Conference on Intelligent Technologies (CONIT), Hubli, India, pp: 1-6.
• Natarajan VA, Babitha M, Kumar MS. 2020. Detection of disease in tomato plants using deep learning techniques. Int J Mod Agric, 9(4): 525-540.
• Öztürk İ. 2024. Determination of tomato bacterial speck disease (Pseudomonas syringae pv. tomato) in tomato plants grown in greenhouses using image processing techniques. MSc thesis, Erciyes University, Institute of Science, Kayseri, Türkiye, pp: 33-36.
• Rahman SU, Alam F, Ahmad N, Khan A, Rehman A, Iqbal M, Ali R. 2023. Image processing-based system for the detection, identification and treatment of tomato leaf diseases. Multimed Tools Appl, 82: 9431-9445.
• Reis Pereira M, Dos Santos FN, Tavares F, Cunha M. 2023. Enhancing host-pathogen phenotyping dynamics: early detection of tomato bacterial diseases using hyperspectral point measurement and predictive modeling. Front Plant Sci, 14: 1242201.
• Sharma J, Mahajan S, Singh S. 2025. Deep learning-based ensemble model for accurate tomato leaf disease classification by leveraging ResNet50 and MobileNetV2 architectures. Sci Rep, 15(1): 98015.
• Shehu HA, Ackley A, Mark M, Eteng OE. 2025. Early detection of tomato leaf diseases using transformers and transfer learning. Eur J Agron, 168: 127625.
• Soeb MJA, Jubayer MF, Tarin TA, Rahman MM, Akter M, Hossain MI. 2023. Tea leaf disease detection and identification based on YOLOv7 (YOLO-T). Sci Rep, 13: 6078.
• Tan L, Lu J, Jiang H. 2021. Tomato leaf diseases classification based on leaf images: a comparison between classical machine learning and deep learning methods. Agri Eng, 3(3): 542-558.
• Taylor JB. 1986. Biosystematics of the tomato. In: Atherton JG, Rudich J, editors. The tomato crop: a scientific basis for improvement. Chapman and Hall, London, UK, pp: 1-34.
• 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.
• TÜİK. 2024. Turkish Statistical Institute: Crop production statistics - 2023 results. URL: https://data.tuik.gov.tr (accessed date: August 5, 2025).