International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 05 | May 2025
p-ISSN: 2395-0072
www.irjet.net
PlantoScope: A CNN-Based Mobile App for Plant Disease Diagnosis Mr. Shubham Paliwal, Mr. Abhishek Purohit Student of B.Tech Computer Science and Engineering, Bikaner Technical University, Bikaner, Rajasthan, India Assistant Professor, Department of Computer Science, Bikaner Technical University, Bikaner, Rajasthan, India ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract - Agriculture forms the backbone of many economies, yet farmers often struggle to detect plant diseases early, leading to significant crop losses. Recent advancements in artificial intelligence have shown promising applications in agriculture, especially in disease diagnosis using image processing. This paper introduces PlantoScope, a convolutional neural network (CNN)-based mobile application designed for real-time plant disease diagnosis through leaf images. The model is trained on the PlantVillage dataset comprising 38 distinct plant classes and diseases. The application allows users to capture or upload leaf images, which are then analyzed by a deep learning model deployed via a Flask API. The output includes the plant type, disease name, cause, and recommended cure. The system achieves an accuracy of 96% using a .h5 model and 94% using a compressed .tflite version, making it viable for mobile deployment. This solution is designed to be scalable and farmer-friendly, with plans to integrate thermal imaging and a binary leaf classifier in the future.
PlantoScope aims to bridge the gap between modern AI tools and the needs of farmers by offering an easy-to-use, realtime disease identification system. 2. RELATED WORK Recent years have witnessed significant advancements in the use of deep learning for agricultural applications. Several studies have demonstrated the efficacy of Convolutional Neural Networks (CNNs) in plant disease identification using image-based datasets. Mohanty et al. (2016) were among the first to use deep learning models on the PlantVillage dataset, achieving over 99% accuracy on test data using AlexNet and GoogLeNet architectures. Their work validated the potential of image classification models for field-level disease detection. Ferentinos (2018) further extended this line of research by evaluating multiple CNN architectures, including VGG and AlexNet, across several plant species and disease categories. His study confirmed CNNs’ robustness even in complex classification tasks involving multiple classes and subtle leaf texture variations.
Key Words: Plant disease detection, Convolutional Neural Network (CNN), Mobile application, Deep learning, Flask API, TensorFlow, Agriculture, PlantVillage, Image classification
However, most of the existing research has focused on model accuracy in offline environments. Limited work has been done to translate these models into lightweight, real-time mobile applications accessible to end-users, particularly farmers.
1. INTRODUCTION Agriculture is a vital sector in many developing nations, where crop health directly affects economic stability and food security. Early detection of plant diseases plays a critical role in ensuring high crop yields and minimizing losses. Traditionally, farmers rely on visual inspection or expert advice, which may be subjective, time-consuming, and inaccessible in remote regions.
This gap in deployment-focused research forms the motivation for PlantoScope, which not only achieves high classification accuracy but also delivers the functionality through a user-friendly mobile interface with TensorFlow Lite integration.
With the rise of deep learning and image processing, automated plant disease detection has become a promising alternative. Convolutional Neural Networks (CNNs) have proven particularly effective for image classification tasks, including plant pathology.
3. DATASET AND PREPROCESSING The proposed model was trained on the publicly available PlantVillage dataset sourced from Kaggle. It consists of 54,305 images of 14 different plants across 38 classes, each representing a specific combination of plant type and disease condition, such as Apple___Black_rot, Tomato___Leaf_Mold, and Corn_(maize)___Common_rust_.
This paper presents PlantoScope, a mobile-based plant disease diagnosis application powered by a CNN model. By capturing or uploading an image of a leaf, users receive an instant prediction of the plant type, disease name, possible cause, and recommended cure. The backend model is trained on the well-known PlantVillage dataset, and the application is optimized for deployment using TensorFlow Lite.
© 2025, IRJET
|
Impact Factor value: 8.315
It consists of images of 14 different plants, namely- Tomato, Strawberry. Squash, Soybean, Raspberry, Potato, Bell Pepper, Peach, Orange, Grape, Corn (Maize), Cherry, Blueberry, Apple
|
ISO 9001:2008 Certified Journal
|
Page 1644