Update app.py

app.py

@@ -1,6 +1,84 @@
 import gradio as gr
 from utils.cad_operations import create_cad_model
 from utils.toolpath_generation import generate_toolpath, generate_gcode
+import cv2
+import pytesseract
+import pandas as pd
+from PIL import Image
+import re
+
+# Path to your Tesseract executable
+pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
+
+# Function to preprocess the image (grayscale, thresholding, etc.)
+def preprocess_image(image_path):
+    # Read the image using OpenCV
+    img = cv2.imread(image_path)
+    
+    # Convert to grayscale
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    
+    # Apply thresholding
+    _, thresh = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY)
+    
+    # Optional: Remove noise (you can experiment with different kernels)
+    kern = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
+    processed_image = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kern)
+    
+    return processed_image
+
+# Function to extract text from image using OCR
+def extract_text_from_image(image):
+    # Use pytesseract to do OCR on the preprocessed image
+    text = pytesseract.image_to_string(image)
+    return text
+
+# Function to extract invoice details using regular expressions
+def extract_invoice_details(text):
+    # Example patterns (you can modify them based on the format of your invoices)
+    invoice_number = re.search(r'Invoice Number[:\s]*([A-Za-z0-9]+)', text)
+    customer_name = re.search(r'Customer Name[:\s]*([\w\s]+)', text)
+    date = re.search(r'Date[:\s]*([\d/]+)', text)
+    total_amount = re.search(r'Total Amount[:\s]*([\d,]+)', text)
+    
+    # Extract matched values or set to 'N/A' if not found
+    invoice_details = {
+        'Invoice Number': invoice_number.group(1) if invoice_number else 'N/A',
+        'Customer Name': customer_name.group(1) if customer_name else 'N/A',
+        'Date': date.group(1) if date else 'N/A',
+        'Total Amount': total_amount.group(1) if total_amount else 'N/A',
+    }
+    return invoice_details
+
+# Function to save extracted data to Excel
+def save_to_excel(data, output_file):
+    # Convert the data to a pandas DataFrame and save it to an Excel file
+    df = pd.DataFrame(data)
+    df.to_excel(output_file, index=False)
+
+def main():
+    # Path to the invoice image
+    image_path = 'path_to_your_invoice_image.jpg'
+    
+    # Preprocess the image
+    preprocessed_image = preprocess_image(image_path)
+    
+    # Extract text from the image using OCR
+    extracted_text = extract_text_from_image(preprocessed_image)
+    
+    # Extract invoice details using regex
+    invoice_details = extract_invoice_details(extracted_text)
+    
+    # Save extracted data to an Excel file
+    output_file = 'extracted_invoice_data.xlsx'
+    save_to_excel([invoice_details], output_file)
+    
+    print(f"Data extracted and saved to {output_file}")
+
+# Run the script
+if __name__ == "__main__":
+    main()
+
 
 # Step 1: Collect user input parameters
 def cnc_workflow(length, width, height, material, tool_size, operation_type):