Rice leaf diseases are detrimental to rice crops, significantly impacting food production and the livelihoods of farmers. Diseases like Bacterial Leaf Blight, Brown Spot, Leaf Blast, and others can reduce yield and quality, leading to economic losses and food scarcity.
This app is designed to detect the specific disease affecting a rice plant. If the plant is healthy, the app will display "Healthy." If an inappropriate image is uploaded, such as a human image instead of a rice leaf, the app will prompt the user to upload a proper image.
This rice leaf disease dataset was sourced from both online resources and independent collection efforts. It consists of a total of 2627 images, categorized into six types of rice leaf diseases for training and validation purposes. The categories included are:
- Bacterial Leaf Blight
- Brown Spot
- Healthy
- Leaf Blast
- Leaf Scald
- Narrow Brown Spot
The dataset can be accessed here.
- Disease Detection: Accurately identifies the type of disease affecting the rice plant, or confirms if the plant is healthy.
- Prevention Resources: Includes dedicated pages with information on preventing and treating each identified disease.
- Shop Option: Users can purchase prevention items directly through the app.
- Weather Updates: Displays live location weather and forecasts for the next two days.
- Image Upload: Allows users to upload images through the gallery or camera for disease detection.
- User Authentication: Features secure login, password recovery, and protection of user details.
This project offers a valuable tool for the agricultural community by automating the detection of rice leaf diseases. By enabling faster diagnosis and intervention, the app helps reduce crop losses, contributes to food security, and supports the economic stability of farmers.
To run this project successfully, make sure you have the following prerequisites:
- Python: Core programming language for deep learning tasks.
- TensorFlow: Necessary for implementing deep learning models such as Vision Transformer, AlexNet, YOLO v5, and YOLO v8.
- NumPy and Pandas: Essential for numerical operations and data manipulation.
- Google Colab: Optional but recommended for faster GPU-based training.
- OpenCV: For image processing and manipulation tasks.
- Torch: Required for specific deep learning implementations, especially YOLO models.
- After downloading the project files, open the project in Android Studio.
- In the terminal, run:
flutter pub get
- Set up your device (either a physical device or an emulator).
- Run the
main.dartfile.
You can view a demo of the project on YouTube: Rice Leaf Disease Detection Demo
Additionally, the design can be viewed on Figma: Project Design on Figma
- Anish Borkar
- D Veera Harsha Vardhan Reddy
- Godavarthi Sai Nikhil
- N Karthik Raja
- V Sai Sumanth
We extend our sincere gratitude to Dr. Manisha Saini & Dr. Himanshu Upreti for being our guiding force throughout this journey. Their mentorship and insights have been instrumental to the success of our project.
For further details, please contact: