Ayurveda---Medicinal-Plant-Classification-Using-Ensemble-Learning-Techniques

Ayurveda---Medicinal-Plant-Classification-Using-Ensemble-Learning-Techniques

 

Python Code

# -*- coding: utf-8 -*-
"""
Created on Fri Mar 17 23:34:05 2023
 
@author: UBED
"""
'''
 
 
from tensorflow.keras.preprocessing import image
from tensorflow.keras.utils import load_img
from keras.models import load_model
import os
from flask import Flask, flash, request, redirect, url_for,jsonify
 
 
 
from werkzeug.utils import secure_filename
import numpy as np
from PIL import Image
from flask import Flask, render_template, request
 
result = {
          0: 'Amaranthus Green', 1: 'Amaranthus Red', 2: 'Balloon vine', 3: 'Betel Leaves', 4: 'Black Night Shade', 5: 'Celery', 6: 'Chinese Spinach', 7: 'Coriander Leaves', 8: 'Curry Leaf',
          9: 'Dwarf Copperleaf (Green)', 10: 'Dwarf copperleaf (Red)', 11: 'False Amarnath', 12: 'Fenugreek Leaves', 13: 'Giant Pigweed', 14: 'Gongura', 15: 'Indian pennywort', 16: 'Lagos Spinach',
          17: 'Lambs Quarters', 18: 'Lettuce Tree', 19: 'Malabar Spinach (Green)', 20: 'Mint Leaves', 21: 'Mustard', 22: 'Palak', 23: 'Siru Keerai', 24: 'Water Spinach'
        }
 
#Predicting Image
MODEL_PATH = 'CNN_model.h5'
model_dl = load_model(MODEL_PATH)
 
 
app = Flask(__name__)
 
@app.route("/")
def hello_world():
 
    return render_template("index.html")
    # return "<p>Hello, World!</p>"
 
 
@app.route('/upload', methods=['POST'])
def upload():
    if 'file' not in request.files:
        return 'No file uploaded.', 400
 
    file = request.files['file']
    if file.filename == '':
        return 'No file selected.', 400
 
    # Save the file to the "image" folder
    file.save(os.path.join('image', file.filename))
 
    temp_path = os.path.join('image',file.filename)
 
    # Preprocess the image for the model
    img = image.load_img(temp_path, target_size=(224, 224))
    img_arr = np.expand_dims(img, axis=0)
    img_arr = image.img_to_array(img)
    img_arr = np.vstack([img_arr])
 
    # Make a prediction with the model
    Result = model_dl.predict(img_arr)
    prediction_index = np.argmax(Result)
    # print(Result,prediction_index)
    prediction = result[prediction_index]
 
    # Remove the temporary file
    # os.remove(temp_path)
 
    # Return the prediction as a JSON response
    response = {'prediction': str(prediction)}
    return jsonify(response)
 
 
if __name__ == '__main__':
    app.run()
 
'''
 
 
from tensorflow.keras.preprocessing import image
from tensorflow.keras.utils import load_img
from keras.models import load_model
import os
from flask import Flask, flash, request, redirect, url_for,jsonify
 
 
 
from werkzeug.utils import secure_filename
import numpy as np
from PIL import Image
from flask import Flask, render_template, request
 
import tempfile
app=Flask(__name__)
 
result  = {0: 'Amaranthus Green', 1: 'Amaranthus Red', 2: 'Balloon vine', 3: 'Betel Leaves', 4: 'Black Night Shade', 5: 'Celery', 6: 'Chinese Spinach', 7: 'Coriander Leaves', 8: 'Curry Leaf', 9: 'Dwarf Copperleaf (Green)', 10: 'Dwarf copperleaf (Red)', 11: 'False Amarnath', 12: 'Fenugreek Leaves', 13: 'Giant Pigweed', 14: 'Gongura', 15: 'Indian pennywort', 16: 'Lagos Spinach', 17: 'Lambs Quarters', 18: 'Lettuce Tree', 19: 'Malabar Spinach (Green)', 20: 'Mint Leaves', 21: 'Mustard', 22: 'Palak', 23: 'Siru Keerai', 24: 'Water Spinach'}
MODEL_PATH =   'CNN_model.h5'
 
model_dl = load_model(MODEL_PATH)
@app.route('/predict', methods=['GET', 'POST'])
def predict():
    if request.method == 'POST':
        img_file = request.files['image']
 
        # Save the temporary file
        with tempfile.NamedTemporaryFile(delete=False) as temp:
            img_file.save(temp.name)
            temp_path = temp.name
 
        # Preprocess the image for the model
        img = image.load_img(temp_path, target_size=(224, 224))
        img_arr = image.img_to_array(img)
        img_arr = np.expand_dims(img_arr, axis=0)
        img_arr = np.vstack([img_arr])
 
        # Make a prediction with the model
        Result = model_dl.predict(img_arr)
        prediction_index = np.argmax(Result)
        prediction = result[prediction_index]
 
        # Remove the temporary file
        os.remove(temp_path)
 
        # Return the prediction as a JSON response
        response = {'prediction': str(prediction)}
        return jsonify(response)
    else:
        return "No image passed UBED"
 
 
if __name__ == '__main__':
    app.run()

HTML CODE

 
<head>
    <meta charset="UTF-8">
    <title>TYEDI</title>
    <link rel="stylesheet" href="{{ url_for('static', filename='css/app.css') }}">
</head>
<body>
  <header>
    <div id="nav_heading">
        MEDICINAL  PLANT FINDER?
      </div>
    </header>
    <section>
      <div class="container">
        <div id="heading">
          GET THE INFO ABOUT THE PLANT 
        </div>
        <div id="subheading">
            Upload the image the find which type of medicinal plant it is.
          </div>
        <div id="uploadDiv">Select the IMAGE</div>           
      </div>
    </section>
    <script src="{{ url_for('static', filename='js/app.js') }}"></script>
  </body>
</html>

CSS Code

@import url(https://fonts.googleapis.com/css?family=Roboto:300);
 
.sw* {
  margin: 0;
}
 
body{
    /* font-family: "Gill Sans Extrabold", sans-serif; */
    background-color: #ecfdf3;
}
#nav_heading {
  padding:10px;
  height: 50px;
  text-align: center;
  line-height: 50px;
  font-weight: bolder;
  font-size: 2.5rem;
  background-color: #fff;
  box-shadow: rgba(10, 160, 35, 0.15) 0px 48px 200px 0px;
 
  font-family: 'Roboto Slab', serif;
}
 
section{
    height:calc(100vh - 70px);
    display: flex;
    flex-direction: column;
    align-items: center;
    justify-content: center;
    box-shadow: rgba(42, 8, 234, 0.15) 0px 48px 100px 0px;
}
section .container{
    display: flex;
    flex-direction: column;
    align-items: center;
    justify-content: center;
    width:500px;
 
    height:300px;
    border-radius: 1rem;
    background: #2cbc63;
    border: 2px solid #033510;
}
 
#heading{
    /* margin-top:-1rem; */
    font-size: 1.8rem;
}
 
#uploadDiv{
    margin-top:2rem;
    width: 150px;
    height:70px;
    background-color:#fff;
    border: 2px solid #033510;
    border-radius: 0.5rem;
    line-height:70px;
    text-align: center;
    font-weight: 600;
 
    font-family: 'Roboto Slab', serif;
    box-shadow: rgba(0, 0, 0, 0.25) 0px 0.0625em 0.0625em, rgba(0, 0, 0, 0.25) 0px 0.125em 0.5em, rgba(255, 255, 255, 0.1) 0px 0px 0px 1px inset;
}
 
#uploadDiv:hover{
    cursor:pointer;
}
 
#uploadDiv:active{
    transform: scale(0.95);
}

JavaScript Code

console.log('yes')
document.getElementById('uploadDiv').addEventListener('click', function() {
    let input = document.createElement('input');
    input.type = 'file';
    input.accept = 'image/*';
 
    input.onchange = function(e) {
      let file = e.target.files[0];
      let formData = new FormData();
      formData.append('file', file);
 
      fetch('/upload', {
        method: 'POST',
        body: formData
      })
      .then(response => response.text())
      .then(result => {
        console.log(result);
      })
      .catch(error => {
        console.error('Error:', error);
      });
    };
 
    input.click();
  });