🌾 CropSense

Landless or marginal farmers lack the resources to either buy or lease more land or invest in farm infrastructure. In order to mitigate this agrarian crisis in the current status quo, there is a need for better recommendation systems to alleviate the crisis by helping the farmers to make an informed decision before starting the cultivation of crops.

To recommend optimum crops to be cultivated by farmers based on several parameters and help them make an informed decision before cultivation The major parameters considered here are:

Soil Quality (N, P, K values respectively)
Humidity
Temperature
Rainfall

Plant Disease Detection

Monitoring the crop's health is as important as ensuring the sufficiency of all other parameters. A ResNet transfer learning model is used for high-end image recognition. The model is trained on different classes of images with different plant diseases and then the model is evaluated using the testing dataset.

:pushpin: DATASET

RECOMMENDATION SYSTEM

The dataset reference was taken from https://www.kaggle.com/datasets/atharvaingle/crop-recommendation-dataset
The dataset contains various parameters such as the soil's N, P, and K values and the overall climatic conditions that support the growth of certain crops.
The dataset used for plant disease detection is the universal Plant Village dataset.

DISEASE DETECTION SYSTEM

The dataset reference was taken from https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset
This dataset consists of about 87K rgb images of healthy and diseased crop leaves which is categorized into 38 different classes.
The total dataset is divided into 80/20 ratio of training and validation set preserving the directory structure. A new directory containing 33 test images is created later for prediction purpose.

:bar_chart: MODULE WORKFLOW

:open_file_folder: Download and Unzip Contents from GitHub Repo

Download and unzip contents from https://github.com/theshredbox/CropSense/tree/main

:green_book: Generating the PKL file

The machine learning model used in this project will first have to be generated by successfully running the included Jupyter notebook. Upon successfully running all code cells, a pickled model for each ML model trained will be created that can be further used for deployment.

:bar_chart:Directory Structure

├── main
│   ├── data
│     ├── Crop Recommendation Dataset
│     ├── Disease Detection Dataset (Gdrive link)
│     
│   ├── src
│     ├── data visualization
│     ├── tasks
│     ├── codes
│     ├── deployment
├── License
├── requirements.txt    
├── README.md
└── .gitignore

Contributing

Contributions to the Crop Recommendation System are welcome! If you would like to contribute, please follow these guidelines:

Fork the repository.
Create a new branch for your feature or bug fix: git checkout -b feature-name.
Make the necessary changes and commit them.
Push your branch to your forked repository: git push origin feature-name.
Submit a pull request to the main repository.

License

This project is licensed under the MIT License. Feel free to modify and distribute the code

theshredbox / CropSense

readme