Update app.py

app.py

@@ -1,57 +1,120 @@
-from fastapi import FastAPI, File, UploadFile
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.middleware.gzip import GZipMiddleware
+import gradio as gr
+import tensorflow as tf
+import keras_ocr
+import requests
+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 doctr.io import DocumentFile
-from doctr.models import ocr_predictor
-import io
-
-app = FastAPI()
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"]
-)
-
-# Initialize models once at startup
-ocr_model = ocr_predictor(pretrained=True)
-paddle_ocr = PaddleOCR(lang='en', use_angle_cls=True)
-
-def ocr_with_doctr(file):
-    text_output = ''
-    doc = DocumentFile.from_pdf(file)
-    result = ocr_model(doc)
-    for page in result.pages:
-        for block in page.blocks:
-            for line in block.lines:
-                text_output += " ".join([word.value for word in line.words]) + "\n"
-    return text_output
-
+from save_data import flag
+            
+"""
+Paddle OCR
+"""
 def ocr_with_paddle(img):
     finaltext = ''
-    result = paddle_ocr.ocr(img)
+    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
+        finaltext += ' '+ text
     return finaltext
 
-def generate_text_from_image(img):
-    return ocr_with_paddle(img)
+"""
+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
 
-@app.post("/ocr/")
-async def perform_ocr(file: UploadFile = File(...)):
-    file_bytes = await file.read()
-    if file.filename.endswith('.pdf'):
-        text_output = ocr_with_doctr(io.BytesIO(file_bytes))
+"""
+easy OCR
+"""
+# gray scale image
+def get_grayscale(image):
+    return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+# 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
+        
+"""
+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:
-        img = np.array(Image.open(io.BytesIO(file_bytes)))
-        text_output = generate_text_from_image(img)
-    return {"ocr_text": text_output}
+        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
+    
+
+"""
+Create user interface for OCR demo
+"""
 
-@app.get("/test/")
-async def test_call():
-    return {"message": "Hi. I'm running"}
+# image = gr.Image(shape=(300, 300))
+image = gr.Image()
+method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR")
+output = gr.Textbox(label="Output")
+
+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:[email protected]" target="_blank">[email protected]</a> 
+                    <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>"""
+    
+
+)
+# demo.launch(enable_queue = False)
+demo.launch(show_error=True)