https://github.com/roshannaidu/ai-for-wheat-disease

As part of my University RA, I developed a Deep Learning model capable of detecting diseased wheat leaves amongst the healthy ones with favourable scores.
https://github.com/roshannaidu/ai-for-wheat-disease

ai crop deep-learning image-processing neural-network python research sklearn supervised-learning wheat

Last synced: about 2 months ago
JSON representation

As part of my University RA, I developed a Deep Learning model capable of detecting diseased wheat leaves amongst the healthy ones with favourable scores.

• Host: GitHub
• URL: https://github.com/roshannaidu/ai-for-wheat-disease
• Owner: RoshanNaidu
• License: mit
• Created: 2024-07-01T19:55:01.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-07-09T22:42:35.000Z (6 months ago)
• Last Synced: 2024-07-10T02:45:04.155Z (6 months ago)
• Topics: ai, crop, deep-learning, image-processing, neural-network, python, research, sklearn, supervised-learning, wheat
• Language: Jupyter Notebook
• Homepage:
• Size: 150 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# AI-for-Wheat-Disease

As part of my University RA, I developed a Deep Learning model capable of detecting diseased wheat leaves amongst the healthy ones with favourable scores and help the user(mostly farmers) classify the healthy vs diseased wheat plants.

# Dataset

The [dataset](https://drive.google.com/drive/folders/1OHKtwD1UrdmhqxrpQEeF_X_pqKotxRGD) contains 4800 images in total with

- 1279 Healthy Wheat

- 939 Wheat Loose Smut

- 1622 Leaf Rust

- 960 (after refining) Crown and Root Rot

# Model

A new type of technique has been utilised (by browsing multiple sources) of classifying each type of plant image into a binary array (4 arrays used) for a favourable and easy classification portrayal alongside using Neural Networks.

For a small cycle of 30 epochs only (faster model result check), a favourable score of 87.31% accuracy has been achieved.

# Contact

Feel free to contact me on my [LinkedIn](https://www.linkedin.com/in/roshan-naidu-aka-adonis).