Design a mobile application to detect tomato plant diseases based on deep learning

Marwa Abdulla, Ali Marhoon

Abstract


Plant diseases consider the most dominant matter for farmers' concerns becausethe operation of discovering and dealing with them requires accuracy, experience, and time. Therefore, this paper proposes an approach to classify seven varieties of tomato diseases using deep learning models. A dataset of 10448 images from PlantVillage and google utilize to train the deep learning (CNN models). The trained models proved their ability to classify with high accuracy, as the highest testing accuracy reached 95.71% for the proposed model for 50 epochs only. The resulted best model is published to a mobile application using the android studioplatform, this application enables the farmer to classify plant diseases accurately and easily. The proposed model and mobile application could be extended to classify as many plant diseases as possible.


Keywords


Android studio; CNN models; Deep learning; Mobile application; Tomato disease

Full Text:

PDF


DOI: https://doi.org/10.11591/eei.v11i5.3918

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats