Update app.py

app.py

@@ -1,46 +1,84 @@
-import gradio as gr
 import pytesseract
 import cv2
 import numpy as np
+from flask import Flask, request, jsonify
+from flask_cors import CORS
 from PIL import Image
 import base64
 
-# Path to Tesseract executable
+# Initialize Flask App
+app = Flask(__name__)
+CORS(app)
+
+# Specify the Tesseract executable path (update this path if needed)
 pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
 
-# Function to decode image
-def decode_image(image):
-    # Convert PIL Image to OpenCV format
-    image = np.array(image)
-    return cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
 
-# Function to process and extract text
-def extract_text(image):
+def decode_base64_image(image_data):
+    """
+    Decode a Base64 image into OpenCV format.
+    """
     try:
-        # Decode the image
-        decoded_image = decode_image(image)
-        
-        # Convert to grayscale
-        gray_image = cv2.cvtColor(decoded_image, cv2.COLOR_BGR2GRAY)
-        
-        # Preprocess the image (optional)
-        _, processed_image = cv2.threshold(gray_image, 127, 255, cv2.THRESH_BINARY)
-        
+        header, encoded = image_data.split(",", 1)
+        image_bytes = base64.b64decode(encoded)
+        np_array = np.frombuffer(image_bytes, np.uint8)
+        image = cv2.imdecode(np_array, cv2.IMREAD_COLOR)
+        return image
+    except Exception as e:
+        return None, f"Error decoding image: {str(e)}"
+
+
+def preprocess_image(image):
+    """
+    Preprocess the image for better OCR results.
+    """
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)  # Convert to grayscale
+    _, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)  # Thresholding
+    return binary
+
+
+@app.route('/extract-text', methods=['POST'])
+def extract_text():
+    """
+    Extract text from an uploaded image.
+    """
+    try:
+        data = request.json
+        if "image" not in data:
+            return jsonify({"error": "No image provided"}), 400
+
+        # Decode the Base64 image
+        image, error = decode_base64_image(data["image"])
+        if error:
+            return jsonify({"error": error}), 400
+
+        # Preprocess the image
+        preprocessed_image = preprocess_image(image)
+
         # Extract text using Tesseract
-        text = pytesseract.image_to_string(processed_image, config="--oem 3 --psm 6")
-        return text
+        text = pytesseract.image_to_string(preprocessed_image, config="--oem 3 --psm 6")
+        return jsonify({"text": text}), 200
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
+@app.route('/status', methods=['GET'])
+def status():
+    """
+    Health check endpoint to verify the server is running.
+    """
+    return jsonify({"status": "Server is running"}), 200
+
+
+if __name__ == '__main__':
+    try:
+        # Ensure Tesseract is installed
+        version = pytesseract.get_tesseract_version()
+        print(f"Tesseract OCR version: {version}")
     except Exception as e:
-        return f"Error: {str(e)}"
-
-# Gradio Interface
-interface = gr.Interface(
-    fn=extract_text,
-    inputs=gr.Image(type="pil", label="Upload Image"),
-    outputs=gr.Textbox(label="Extracted Text"),
-    title="Text Extraction App",
-    description="Upload an image of an invoice or document to extract text."
-)
-
-# Run the app
-if __name__ == "__main__":
-    interface.launch()
+        print(f"Error: {e}")
+        print("Ensure Tesseract-OCR is installed and the path is correctly set.")
+        exit(1)
+
+    # Start the Flask server
+    app.run(debug=True, host='0.0.0.0', port=5000)