Update app.py

app.py

@@ -1,129 +1,34 @@
 import gradio as gr
-import cv2
-import numpy as np
-import pytesseract
-from PIL import Image
+from PyPDF2 import PdfReader
 import io
-import matplotlib.pyplot as plt
 
-# Configure pytesseract path (adjust this based on your installation)
-# pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'  # Uncomment and modify for Windows
-
-def preprocess_image(image):
-    """Preprocess the image to improve OCR accuracy for handwritten text"""
-    # Convert to grayscale if it's a color image
-    if len(image.shape) == 3:
-        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+# Function to convert PDF to text (handles both byte data and file uploads)
+def pdf_to_text(file_input):
+    # If the input is in byte format (i.e., it comes as raw bytes from a file or Base64 encoding)
+    if isinstance(file_input, bytes):
+        # Treat it as byte data and convert it to a file-like object
+        pdf_file = io.BytesIO(file_input)
     else:
-        gray = image.copy()
-    
-    # Apply adaptive thresholding
-    thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
-                                   cv2.THRESH_BINARY_INV, 11, 2)
-    
-    # Noise removal using morphological operations
-    kernel = np.ones((1, 1), np.uint8)
-    opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
-    
-    # Dilate to connect components
-    kernel = np.ones((2, 2), np.uint8)
-    dilated = cv2.dilate(opening, kernel, iterations=1)
-    
-    return dilated
-
-def perform_ocr(input_image):
-    """Process the image and perform OCR"""
-    if input_image is None:
-        return "No image provided", None
-    
-    # Convert from RGB to BGR (OpenCV format)
-    image_np = np.array(input_image)
-    if len(image_np.shape) == 3:
-        image_np = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
-    
-    # Preprocess the image
-    preprocessed = preprocess_image(image_np)
-    
-    # Convert back to PIL for visualization
-    pil_preprocessed = Image.fromarray(preprocessed)
-    
-    # Use pytesseract with specific configurations for handwritten text
-    custom_config = r'--oem 3 --psm 6 -l eng -c preserve_interword_spaces=1 tessedit_char_whitelist="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789.,;:\'\"()[]{}!?-+*/=><_%$#@&|~^`\\ "' 
-    
-    # Perform OCR
-    extracted_text = pytesseract.image_to_string(pil_preprocessed, config=custom_config)
-    
-    # Return the extracted text and the preprocessed image for visualization
-    return extracted_text, pil_preprocessed
+        # If it's a regular PDF file (file upload), open it from the file input
+        pdf_file = file_input.name  # This will get the file path if it's a regular file upload
 
-def ocr_pipeline(input_image):
-    """Complete OCR pipeline with visualization"""
-    
-    extracted_text, preprocessed_image = perform_ocr(input_image)
-    
-    # Create visualization
-    if input_image is not None and preprocessed_image is not None:
-        fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 6))
-        ax1.imshow(input_image)
-        ax1.set_title("Original Image")
-        ax1.axis("off")
-        
-        ax2.imshow(preprocessed_image, cmap='gray')
-        ax2.set_title("Preprocessed Image")
-        ax2.axis("off")
-        
-        plt.tight_layout()
-        
-        # Convert plot to image
-        buf = io.BytesIO()
-        plt.savefig(buf, format='png')
-        buf.seek(0)
-        viz_img = Image.open(buf)
-        plt.close(fig)
-        
-        return extracted_text, viz_img
-    
-    return extracted_text, None
+    try:
+        reader = PdfReader(pdf_file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
+        return text
+    except Exception as e:
+        return f"Error while processing the PDF: {str(e)}"
 
-# Create the Gradio interface
-with gr.Blocks(title="Handwritten OCR App") as app:
-    gr.Markdown("# Handwritten Text OCR Extraction")
-    gr.Markdown("""
-    This app extracts text from handwritten notes. 
-    Upload an image containing handwritten text and the app will convert it to digital text.
-    """)
-    
-    with gr.Row():
-        with gr.Column():
-            input_image = gr.Image(type="pil", label="Upload Handwritten Image")
-            run_button = gr.Button("Extract Text")
-        
-        with gr.Column():
-            output_text = gr.Textbox(label="Extracted Text", lines=15)
-            processed_image = gr.Image(label="Preprocessing Visualization")
-    
-    run_button.click(
-        fn=ocr_pipeline,
-        inputs=input_image,
-        outputs=[output_text, processed_image]
-    )
-    
-    gr.Markdown("""
-    ## Tips for better results:
-    - Ensure good lighting and contrast in the image
-    - Try to keep the text as horizontal as possible
-    - Clear handwriting works best
-    - For better results, you may need to crop the image to focus on specific sections
-    """)
-    
-    # Add example images
-    gr.Examples(
-        examples=[
-            "handwritten_sample.jpg",  # Replace with your example image paths
-        ],
-        inputs=input_image,
-    )
+# Gradio interface: allow both file uploads and byte data input
+iface = gr.Interface(
+    fn=pdf_to_text,  # Function to call for text extraction
+    inputs=gr.File(label="Upload PDF or send Byte data"),  # File input
+    outputs="text",  # Output the extracted text
+    title="PDF to Text Conversion",
+    description="Upload a PDF file or send byte data (Base64 encoded) to extract its text."
+)
 
-# Launch the app
 if __name__ == "__main__":
-    app.launch()
+    iface.launch()