Update app.py

app.py

@@ -1,74 +1,120 @@
-from flask import Flask, request, jsonify, render_template
-from google.cloud import vision
-import io
-import pandas as pd
+import gradio as gr
+import tensorflow as tf
+import keras_ocr
 import requests
-from salesforce_api import Salesforce
-from datasets import load_dataset
+import cv2
 import os
+import csv
+import numpy as np
+import pandas as pd
+import huggingface_hub
+from huggingface_hub import Repository
+from datetime import datetime
+import scipy.ndimage.interpolation as inter
+import easyocr
+import datasets
+from datasets import load_dataset, Image
+from PIL import Image
+from paddleocr import PaddleOCR
+from save_data import flag
+            
+"""
+Paddle OCR
+"""
+def ocr_with_paddle(img):
+    finaltext = ''
+    ocr = PaddleOCR(lang='en', use_angle_cls=True)
+    # img_path = 'exp.jpeg'
+    result = ocr.ocr(img)
+    
+    for i in range(len(result[0])):
+        text = result[0][i][1][0]
+        finaltext += ' '+ text
+    return finaltext
 
-app = Flask(__name__)
-
-# Initialize Google Cloud Vision client
-vision_client = vision.ImageAnnotatorClient()
-
-# Initialize Salesforce client
-sf = Salesforce(
-    username='your_salesforce_username',
-    password='your_salesforce_password',
-    security_token='your_salesforce_security_token'
-)
-
-# Load dataset from Hugging Face
-dataset = load_dataset('Ajay98/setajsondataset')
-json_data = pd.DataFrame(dataset['train'])
-
-@app.route('/')
-def index():
-    return render_template('index.html')
-
-@app.route('/upload', methods=['POST'])
-def upload_image():
-    if 'file' not in request.files:
-        return "No file part"
-
-    file = request.files['file']
+"""
+Keras OCR
+"""
+def ocr_with_keras(img):
+    output_text = ''
+    pipeline=keras_ocr.pipeline.Pipeline()
+    images=[keras_ocr.tools.read(img)]
+    predictions=pipeline.recognize(images)
+    first=predictions[0]
+    for text,box in first:
+        output_text += ' '+ text
+    return output_text
 
-    if file.filename == '':
-        return "No selected file"
+"""
+easy OCR
+"""
+# gray scale image
+def get_grayscale(image):
+    return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
 
-    if file:
-        # Extract text from the image
-        extracted_text = extract_text_from_image(file)
+# Thresholding or Binarization
+def thresholding(src):
+    return cv2.threshold(src,127,255, cv2.THRESH_TOZERO)[1]
+def ocr_with_easy(img):
+    gray_scale_image=get_grayscale(img)
+    thresholding(gray_scale_image)
+    cv2.imwrite('image.png',gray_scale_image)
+    reader = easyocr.Reader(['th','en'])
+    bounds = reader.readtext('image.png',paragraph="False",detail = 0)
+    bounds = ''.join(bounds)
+    return bounds
         
-        # Compare extracted text with JSON dataset
-        matched_data = compare_data(extracted_text, json_data)
+"""
+Generate OCR
+"""
+def generate_ocr(Method,img):
+    
+    text_output = ''
+    if (img).any():
+        add_csv = []
+        image_id = 1
+        print("Method___________________",Method)
+        if Method == 'EasyOCR':
+            text_output = ocr_with_easy(img)
+        if Method == 'KerasOCR':
+            text_output = ocr_with_keras(img)
+        if Method == 'PaddleOCR':
+            text_output = ocr_with_paddle(img)
+       
+        try:
+            flag(Method,text_output,img)
+        except Exception as e:
+            print(e)
+        return text_output
+    else:
+        raise gr.Error("Please upload an image!!!!")
+    
+    # except Exception as e:
+    #     print("Error in ocr generation ==>",e)
+    #     text_output = "Something went wrong"
+    # return text_output
+    
 
-        # Update Salesforce with structured data
-        update_salesforce(matched_data)
+"""
+Create user interface for OCR demo
+"""
 
-        return jsonify({"extracted_text": extracted_text, "matched_data": matched_data.to_dict(orient='records')})
+# image = gr.Image(shape=(300, 300))
+image = gr.Image()
+method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR")
+output = gr.Textbox(label="Output")
 
-def extract_text_from_image(image_file):
-    content = image_file.read()
-    image = vision.Image(content=content)
-    response = vision_client.text_detection(image=image)
-    texts = response.text_annotations
-    extracted_text = texts[0].description if texts else ''
-    return extracted_text
+demo = gr.Interface(
+    generate_ocr,
+    [method,image],
+    output,
+    title="Optical Character Recognition",
+    css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
+    article = """<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
+                    <a href="mailto:ajayaklaram@gmail.com" target="_blank">aajayk999@gmail.com</a> 
+                    <p style='text-align: center;'>Developed by: <a href="https://www.sathkrutha.com" target="_blank">sathkrutha tech solutions</a></p>"""
+    
 
-def compare_data(extracted_text, json_data):
-    matches = json_data[json_data['column_name'].str.contains(extracted_text, case=False, na=False)]
-    return matches
-
-def update_salesforce(data):
-    for _, row in data.iterrows():
-        sf.Contact.create({
-            'LastName': row['LastName'],
-            'FirstName': row['FirstName'],
-            'Email': row['Email'],
-            'Phone': row['Phone']
-        })
-
-if __name__ == '__main__':
-    app.run(debug=True)
+)
+# demo.launch(enable_queue = False)
+demo.launch()