Skip to content

DivyamGoyal-github/Agri-Vision-AI

Repository files navigation

Agri-Vision-AI

Mission

To empower farmers with an AI-driven solution that enables early, accessible, and accurate detection of crop diseases, ultimately improving crop yield, reducing pesticide use, and promoting sustainable agriculture.

Objectives

  • Build an AI model that can classify crop diseases from images
  • To give information on various parameters regarding the current crop status
  • Integrate a user-friendly interface for farmers to upload images
  • Link the model output to a language model (LLM) that provides treatment suggestions
  • Support multilingual and voice-based interaction to ensure inclusivity
  • Ensure robustness and scalability of the solution for real-world deployment
  • To generate comprehensive reports regarding the crops, including news of seasonal and anomalous hazards if possible

DataSets Used

After extensive research and evaluation of multiple publicly available plant disease datasets, the following most relevant and diverse sources were selected and merged. Through careful augmentation and balancing, a unified dataset has been created, consisting of 77 well-defined classes with approximately 1,290 images per class, ensuring consistency, diversity, and robustness for model training.

20k-Crop Disease

https://www.kaggle.com/datasets/jawadali1045/20k-multi-class-crop-disease-images?utm_source=chatgpt.com

Plant Village

https://www.kaggle.com/datasets/emmarex/plantdisease

Plantdoc

https://github.com/pratikkayal/PlantDoc-Dataset

Identification of Plant Leaf Diseases Using a 9-layer Deep Convolutional Neural Network

https://data.mendeley.com/datasets/tywbtsjrjv/1

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 5

Languages