Update app.py

app.py

@@ -0,0 +1,151 @@
+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
+import pytesseract
+from pdf2image import convert_from_path
+from PIL import Image
+import os  
+import tempfile
+from openai import OpenAI
+
+# Function to perform OCR
+def ocr(input_file, lang='fas'):  # 'fas': Persian language (Farsi)
+    extracted_text = ""
+    # if isinstance(input_file, Image.Image):  # If the input is an image
+    text = pytesseract.image_to_string(input_file, lang=lang)
+    extracted_text = text
+
+    return extracted_text
+
+"""
+Paddle OCR
+"""
+def ocr_with_paddle(img):
+    finaltext = ''
+    ocr = PaddleOCR(lang='fa', 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
+
+"""
+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
+
+"""
+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(['fa','en'])
+    bounds = reader.readtext('image.png',paragraph="False",detail = 0)
+    bounds = ''.join(bounds)
+    return bounds
+
+"""
+Generate OCR
+"""
+
+def process(input_type, gr_img, lang):
+
+    if isinstance(gr_img, np.ndarray):
+        # Create a temporary file to save the image
+        with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as temp_file:
+            temp_path = temp_file.name
+            # Save the NumPy array as an image file
+            Image.fromarray(gr_img).save(temp_path)
+    
+    image = Image.open(temp_path)
+    # image = file
+    extracted_text = ocr(image, lang)
+    return extracted_text
+
+
+def generate_ocr(Method, img):
+    
+    text_output = ''
+
+    add_csv = []
+    image_id = 1
+    if Method == 'Version3':
+        text_output = process("img", img, "fas")
+
+    if not text_output:
+        return text_output
+    else:
+        client = OpenAI(
+        base_url="https://openrouter.ai/api/v1",
+        api_key="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",  # Get from https://openrouter.ai
+        )
+        
+        response = client.chat.completions.create(
+            model="deepseek/deepseek-r1:free",
+            messages=[{"role": "user", "content": f"""متن زیر پر از ایرادات تایپی و نگارشی است اصلاح کن و فقط متن اصلاح شده رو بهم بده
+                      اطلاعات اظافه رو نیار و فقط متن اصلاح شده رو برگردون
+                      {text_output}
+                    """}]
+        )
+            
+        return response.choices[0].message.content
+
+
+"""
+Create user interface for OCR demo
+"""
+
+# image = gr.Image(shape=(300, 300))
+# image = gr.File(label="Upload PDF/Image")
+image = gr.Image()
+method = "Version3"
+output = gr.Textbox(label="Output")
+
+demo = gr.Interface(
+    generate_ocr,
+    [method, image],
+    output,
+    title="Persian 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://github.com/mohammad2928" target="_blank">Mohammad Mahmoudi</a></p>"""
+    
+
+)
+# demo.launch(enable_queue = False)
+demo.launch(share=True)