/Plant_Leaf_Disease_Detection

Final Year College Project on Plant Leaf Disease Detection with accuracy of 99.5%

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

Plant Leaf Disease Detection

About and Why?

Stats regarding yield loss

Above Image shows total crops lost due to weed, pathogen, Viruses, Animal pests etc etc. so, looking after the stats and increasing poplulation of World it's our small contribution to detect disease in plant leaf so farmers can take proper action and save even if a little amount of crops if possible.

Disease-infected plants usually show obvious marks or lesions on leaves, stems, flowers, or fruits. Generally, each disease or pest condition presents a unique visible pattern that can be used to uniquely diagnose abnormalities. Usually, the leaves of plants are the primary source for identifying plant diseases, and most of the symptoms of diseases may begin to appear on the leaves.

Contributors

Harsh Vardhan - Harsh/Github, Harsh/Linkedin
Rishi Raj - Rishi/Github, Rishi/Linkedin
Vikram Kumar - Vikram/Linkedin

Arpita Dutta - Arpita/Linkedin
Sudip Biswas - Sudip/Linkedin

Database

An image database means storing high quantities of digital images in a particular location. It also means organizing photos so that they can be shared, accessed quickly and easily. In this project we have taken large number of Different Images of crop and Leafs that is available on Internet. Various datasets are available on the internet to detect plant disease and train our model with these datasets. We can also create our own data set and train our model. But here we are thinking of using a dataset that is available on a famous site called “Kaggle”.

Link of Dataset - https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset

Proposed Methadology

  1. Collection of Data and combining various datasets.
  2. Labelling images of respective plant diseases
  3. Perform Data Cleaning, Feature Engineering and Augmentation
  4. Create Basic CNN for achieving baseline results
  5. Implement Transfer Learning Model

  6. Compare and choose the best performing model
  7. Test the model on Test data/Unseen data
  8. Record the results and provide Accuracy
  9. Export Model
  10. Deploy Webapp for Inference

Here’s the overall architecture of the proposed methodology:
Stats regarding yield loss

Tools and Technologies

  • Python
  • TensorFlow
  • Keras
  • Complier Option
  • Jupyter Notebook

Performance (Training and Testing Results)

Attaching below image of trained and tested data
Performance

Deployed Webpage For simple User

Website Link - https://rishi2690-plant-disease-detection-main-bl073h.streamlit.app/

Snapshots of Website Webpage 1
Webpage 2

References

[1] Robert G. de Luna, Elmer P. Dadios, Argel A. Bandala, “Automated Image Capturing System for Deep Learning-based Tomato Plant Leaf Disease Detection and Recognition,” International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD) 2019.

[2] Suma VR Amog Shetty, Rishab F Tated, Sunku Rohan, Triveni S Pujar, “CNN based Leaf Disease Identification and Remedy Recommendation System,” IEEE conference paper 2019.

[3] Peng Jiang, Yuehan Chen, Bin Liu, Dongjian He, Chunquan Liang, “Real-Time Detection of Apple Leaf Diseases Using Deep Learning Approach Based on Improved Convolution Neural Networks,” IEEE ACCESS 2019.

[3] Peng Jiang, Yuehan Chen, Bin Liu, Dongjian He, Chunquan Liang, “Real-Time Detection of Apple Leaf Diseases Using Deep Learning Approach Based on Improved Convolution Neural Networks,” IEEE ACCESS 2019.

[5] Robert G. de Luna, Elmer P. Dadios, Argel A. Bandala, “Automated Image Capturing System for Deep Learning-based Tomato Plant Leaf Disease Detection and Recognition,” Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference.

[6] Omkar Kulkarni, “Crop Disease Detection Using Deep Learning,” IEEE access 2018.