Add PaddleOCR masking and region detection pipeline

- Created PaddleOCR client for remote server communication
- Implemented text masking + region detection pipeline
- Test results: 100% recall on sample PDF (found both signatures)
- Identified issues: split regions, printed text not fully masked
- Documented 5 solution options in PADDLEOCR_STATUS.md
- Next: Implement region merging and two-stage cleaning

paddleocr_client.py

@@ -0,0 +1,169 @@
+#!/usr/bin/env python3
+"""
+PaddleOCR Client
+Connects to remote PaddleOCR server for OCR inference
+"""
+
+import requests
+import base64
+import numpy as np
+from typing import List, Dict, Tuple, Optional
+from PIL import Image
+from io import BytesIO
+
+class PaddleOCRClient:
+    """Client for remote PaddleOCR server."""
+
+    def __init__(self, server_url: str = "http://192.168.30.36:5555"):
+        """
+        Initialize PaddleOCR client.
+
+        Args:
+            server_url: URL of the PaddleOCR server
+        """
+        self.server_url = server_url.rstrip('/')
+        self.timeout = 30  # seconds
+
+    def health_check(self) -> bool:
+        """
+        Check if server is healthy.
+
+        Returns:
+            True if server is healthy, False otherwise
+        """
+        try:
+            response = requests.get(
+                f"{self.server_url}/health",
+                timeout=5
+            )
+            return response.status_code == 200 and response.json().get('status') == 'ok'
+        except Exception as e:
+            print(f"Health check failed: {e}")
+            return False
+
+    def ocr(self, image: np.ndarray) -> List[Dict]:
+        """
+        Perform OCR on an image.
+
+        Args:
+            image: numpy array of the image (RGB format)
+
+        Returns:
+            List of detection results, each containing:
+                - box: [[x1,y1], [x2,y2], [x3,y3], [x4,y4]]
+                - text: detected text string
+                - confidence: confidence score (0-1)
+
+        Raises:
+            Exception if OCR fails
+        """
+        # Convert numpy array to PIL Image
+        if len(image.shape) == 2:  # Grayscale
+            pil_image = Image.fromarray(image)
+        else:  # RGB or RGBA
+            pil_image = Image.fromarray(image.astype(np.uint8))
+
+        # Encode to base64
+        buffered = BytesIO()
+        pil_image.save(buffered, format="PNG")
+        image_base64 = base64.b64encode(buffered.getvalue()).decode('utf-8')
+
+        # Send request
+        try:
+            response = requests.post(
+                f"{self.server_url}/ocr",
+                json={"image": image_base64},
+                timeout=self.timeout
+            )
+            response.raise_for_status()
+
+            result = response.json()
+
+            if not result.get('success'):
+                error_msg = result.get('error', 'Unknown error')
+                raise Exception(f"OCR failed: {error_msg}")
+
+            return result.get('results', [])
+
+        except requests.exceptions.Timeout:
+            raise Exception(f"OCR request timed out after {self.timeout} seconds")
+        except requests.exceptions.ConnectionError:
+            raise Exception(f"Could not connect to server at {self.server_url}")
+        except Exception as e:
+            raise Exception(f"OCR request failed: {str(e)}")
+
+    def get_text_boxes(self, image: np.ndarray) -> List[Tuple[int, int, int, int]]:
+        """
+        Get bounding boxes of all detected text.
+
+        Args:
+            image: numpy array of the image
+
+        Returns:
+            List of bounding boxes as (x, y, w, h) tuples
+        """
+        results = self.ocr(image)
+        boxes = []
+
+        for result in results:
+            box = result['box']  # [[x1,y1], [x2,y2], [x3,y3], [x4,y4]]
+
+            # Convert polygon to bounding box
+            xs = [point[0] for point in box]
+            ys = [point[1] for point in box]
+
+            x = int(min(xs))
+            y = int(min(ys))
+            w = int(max(xs) - min(xs))
+            h = int(max(ys) - min(ys))
+
+            boxes.append((x, y, w, h))
+
+        return boxes
+
+    def __repr__(self):
+        return f"PaddleOCRClient(server_url='{self.server_url}')"
+
+
+# Convenience function
+def create_ocr_client(server_url: str = "http://192.168.30.36:5555") -> PaddleOCRClient:
+    """
+    Create and test PaddleOCR client.
+
+    Args:
+        server_url: URL of the PaddleOCR server
+
+    Returns:
+        PaddleOCRClient instance
+
+    Raises:
+        Exception if server is not reachable
+    """
+    client = PaddleOCRClient(server_url)
+
+    if not client.health_check():
+        raise Exception(
+            f"PaddleOCR server at {server_url} is not responding. "
+            "Make sure the server is running on the Linux machine."
+        )
+
+    return client
+
+
+if __name__ == "__main__":
+    # Test the client
+    print("Testing PaddleOCR client...")
+
+    try:
+        client = create_ocr_client()
+        print(f"✅ Connected to server: {client.server_url}")
+
+        # Create a test image
+        test_image = np.ones((100, 100, 3), dtype=np.uint8) * 255
+
+        print("Running test OCR...")
+        results = client.ocr(test_image)
+        print(f"✅ OCR test successful! Found {len(results)} text regions")
+
+    except Exception as e:
+        print(f"❌ Error: {e}")