article · Journal of Agricultural Engineering
Controlling tomato crop diseases is a significant agricultural challenge where early detection can curb pesticide usage and decrease economic losses. Although deep learning computer vision methods are increasingly applied to crop disease detection, few models are optimised for practical field use. To address this, a disease recognition model was developed and trained using a combination of public datasets and internal image collections. Three distinct deep learning architectures, namely VGG16, Inception_v3, and Resnet50, were trained and evaluated. The resulting model was integrated into a mobile Android application called TomatoGuard. The application identifies healthy leaves alongside nine distinct tomato leaf diseases. Testing demonstrated that TomatoGuard achieved 99 percent accuracy, outperforming the widely used Plantix general-purpose plant disease detection application.
Early detection of tomato diseases allows farmers to intervene before widespread damage occurs, minimising crop losses and cutting down unnecessary pesticide applications. Deploying highly accurate computer vision models directly onto mobile phones provides accessible diagnostic support to growers in the field, helping to safeguard agricultural yields and reduce management costs without requiring specialised laboratory equipment.
The software has been packaged into an Android application named TomatoGuard, placing it near practical deployment for agricultural workers and farm managers. By offering targeted identification for nine specific tomato diseases with 99 percent accuracy, it provides an immediate mobile diagnostic tool for tomato growers that outperforms existing broader plant diagnostic applications.
AI-generated from the published abstract. Always read the original work before citing.
Tomato disease control remains a major challenge in the agriculture sector. Early stage recognition of these diseases is critical to reduce pesticide usage and mitigate economic losses. While many research works have been inspired by the success of deep learning in computer vision to improve the performance of recognition systems for crop diseases, few of these studies optimized the deep learning models to generalize their findings to practical use in the field. In this work, we proposed a model for identifying tomato leaf diseases based on both in-house data and public tomato leaf images databases. Three deep learning network architectures (VGG16, Inception_v3, and Resnet50) were trained and tested. We packaged the trained model into an Android application named TomatoGuard to identify nine kinds of tomato leaf diseases and healthy tomato leaf. The results showed that TomatoGuard could be adopted as a model for identifying tomato diseases with a 99% test accuracy, showing significantly better performance compared with APP Plantix, a widely used APP for general purpose plant disease detection.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.4081/jae.2022.1432
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
