All Projects → soumyajit4419 → Plant_AI

soumyajit4419 / Plant_AI

Licence: MIT license
Performing Leaf Image classification for Recognition of Plant Diseases using various types of CNN Architecture, For detection of Diseased Leaf and thus helping the increase in crop yield.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language
CSS
56736 projects
HTML
75241 projects

Projects that are alternatives of or similar to Plant AI

image features
Extract deep learning features from images using simple python interface
Stars: ✭ 84 (+133.33%)
Mutual labels:  image-classification
tutorials
A tutorial series by Preferred.AI
Stars: ✭ 136 (+277.78%)
Mutual labels:  image-classification
MNIST
Handwritten digit recognizer using a feed-forward neural network and the MNIST dataset of 70,000 human-labeled handwritten digits.
Stars: ✭ 28 (-22.22%)
Mutual labels:  image-classification
stackml-js
Machine Learning platform in-browser for creators
Stars: ✭ 34 (-5.56%)
Mutual labels:  image-classification
zalo-landmark
Zalo AI Challenge - Landmark Identification
Stars: ✭ 39 (+8.33%)
Mutual labels:  image-classification
trojanzoo
TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.
Stars: ✭ 178 (+394.44%)
Mutual labels:  image-classification
ailia-models
The collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+2961.11%)
Mutual labels:  image-classification
image-sorter2
One-click image sorting/labelling script
Stars: ✭ 65 (+80.56%)
Mutual labels:  image-classification
deepstack-ui
UI for working with Deepstack
Stars: ✭ 115 (+219.44%)
Mutual labels:  image-classification
deep-learning
Projects include the application of transfer learning to build a convolutional neural network (CNN) that identifies the artist of a painting, the building of predictive models for Bitcoin price data using Long Short-Term Memory recurrent neural networks (LSTMs) and a tutorial explaining how to build two types of neural network using as input the…
Stars: ✭ 43 (+19.44%)
Mutual labels:  image-classification
ResNet-50-CBAM-PyTorch
Implementation of Resnet-50 with and without CBAM in PyTorch v1.8. Implementation tested on Intel Image Classification dataset from https://www.kaggle.com/puneet6060/intel-image-classification.
Stars: ✭ 31 (-13.89%)
Mutual labels:  image-classification
tensorflow-video-classifier
image classification via video input, frame-by-frame
Stars: ✭ 16 (-55.56%)
Mutual labels:  image-classification
meta-st-stm32mpu-ai
This repository contains the OpenEmbedded meta layer to install AI frameworks and tools for the STM32MP1
Stars: ✭ 32 (-11.11%)
Mutual labels:  image-classification
backprop
Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
Stars: ✭ 229 (+536.11%)
Mutual labels:  image-classification
ros2-tensorflow
ROS2 nodes for computer vision tasks in Tensorflow
Stars: ✭ 41 (+13.89%)
Mutual labels:  image-classification
PyTrx
PyTrx is a Python object-oriented programme created for the purpose of calculating real-world measurements from oblique images and time-lapse image series. Its primary purpose is to obtain velocities, surface areas, and distances from oblique, optical imagery of glacial environments.
Stars: ✭ 31 (-13.89%)
Mutual labels:  image-classification
Evo-ViT
Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
Stars: ✭ 50 (+38.89%)
Mutual labels:  image-classification
favorite-research-papers
Listing my favorite research papers 📝 from different fields as I read them.
Stars: ✭ 12 (-66.67%)
Mutual labels:  image-classification
AlphaTree-graphic-deep-neural-network
AI Roadmap:机器学习(Machine Learning)、深度学习(Deep Learning)、对抗神经网络(GAN),图神经网络(GNN),NLP,大数据相关的发展路书(roadmap), 并附海量源码(python,pytorch)带大家消化基本知识点,突破面试,完成从新手到合格工程师的跨越,其中深度学习相关论文附有tensorflow caffe官方源码,应用部分含推荐算法和知识图谱
Stars: ✭ 2,221 (+6069.44%)
Mutual labels:  image-classification
goexif2
MAINTAINER WANTED -- Decode embedded EXIF meta data from image files written in Pure Golang
Stars: ✭ 35 (-2.78%)
Mutual labels:  image-classification

PLANT-AI [Recognition of Plant Diseases by Leaf Image Classification]

https://plant49-ai.herokuapp.com/

demo

Description

Food security for billions of people on earth requires minimizing crop damage by timely detection of diseases.Developing methods for detection of plant diseases serves the dual purpose of increasing crop yield and reducing pesticide use without knowing about the proper disease. Along with development of better crop varieties, disease detection is thus paramount goal for achieving food security. The traditional method of disease detection has been to use manual examination by either farmers or experts, which can be time consuming and costly, proving infeasible for millions of small and medium sized farms around the world.

This project is an approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. The developed model is able to recognize 38 different types of plant diseases out of of 14 different plants with the ability to distinguish plant leaves from their surroundings.

Leaf Image Classification

batch of image

This process for building a model which can detect the disease assocaited with the leaf image. The key points to be followed are:

  1. Data gathering

    The dataset taken was "New Plant Diseases Dataset". It can be downloaded through the link "https://www.kaggle.com/vipoooool/new-plant-diseases-dataset". It is an Image dataset containing images of different healthy and unhealthy crop leaves.

  2. Model building

    • I have used pytorch for building the model.
    • I used three models:-
      1. The CNN model architecture consists of CNN Layer, Max Pooling, Flatten a Linear Layers.
      2. Using Transfer learning VGG16 Architecture.
      3. Using Transfer learning resnet34 Architecture.
  3. Training

    The model was trained by using variants of above layers mentioned in model building and by varying hyperparameters. The best model was able to achieve 98.42% of test accuracy.

  4. Testing

    The model was tested on total 17572 images of 38 classes.
    The model used for prediction on sample images. It can be seen below:

    index2 index3
  5. Various Model Architecture tried along with Learning Rate and Optimizer and various accuracy obtained with different models.

models

All the version with code can be seen in jovian.ml (https://jovian.ml/soumyajit4419/course-project-plant-disease-classification)

Details about the model

The model will be able to detect 38 types of diseases of 14 Unique plants

  • The detail list of plants and diseases can be seen in List

Further Work:

  • Implementing Image Localisation to find the excat position of the leaf affected .
  • Building Recommender system for recommendation of proper presticides and control method for the disease.
  • Implementing the appropriate management strategies like fungicide applications and pesticide applications could lead to early information on crop health and disease detection.This could facilitate the control of diseases and improve productivity.

Usage:

  • Flask : Code for Flask Server and deployment
  • TestImages : Sample image for model testing
  • Src : All The source code for building models
  • Models : All the Pretrained Models of Pytorch

License

This project is Licensed under MIT

Explanation

To understand the code : You can find the complete explanation to the code in Article

Show your support

Give a if you like this website!

Buy Me A Coffee

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].