gbanyan
8f231da3bc
- Implemented comprehensive feature analysis based on size, stroke length, and regularity - Size-based scoring: height >50px indicates handwriting - Stroke length ratio: >0.4 indicates handwriting - Irregularity metrics: low compactness/solidity indicates handwriting - Successfully tested on sample PDF with 2 signatures (楊智惠, 張志銘) - Created detailed documentation: CURRENT_STATUS.md and NEW_SESSION_HANDOFF.md - Stable PaddleOCR 2.7.3 configuration documented (numpy 1.26.4, opencv 4.6.0.66) - Prepared research plan for PP-OCRv5 upgrade investigation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
92 lines
2.4 KiB
Python
92 lines
2.4 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
PaddleOCR Server v5 (PP-OCRv5)
|
|
Flask HTTP server exposing PaddleOCR v3.3.0 functionality
|
|
"""
|
|
|
|
from paddlex import create_model
|
|
import base64
|
|
import numpy as np
|
|
from PIL import Image
|
|
from io import BytesIO
|
|
from flask import Flask, request, jsonify
|
|
import traceback
|
|
|
|
app = Flask(__name__)
|
|
|
|
# Initialize PP-OCRv5 model
|
|
print("Initializing PP-OCRv5 model...")
|
|
model = create_model("PP-OCRv5_server")
|
|
print("PP-OCRv5 model loaded successfully!")
|
|
|
|
@app.route('/health', methods=['GET'])
|
|
def health():
|
|
"""Health check endpoint."""
|
|
return jsonify({
|
|
'status': 'ok',
|
|
'service': 'paddleocr-server-v5',
|
|
'version': '3.3.0',
|
|
'model': 'PP-OCRv5_server',
|
|
'gpu_enabled': True
|
|
})
|
|
|
|
@app.route('/ocr', methods=['POST'])
|
|
def ocr_endpoint():
|
|
"""
|
|
OCR endpoint using PP-OCRv5.
|
|
|
|
Accepts: {"image": "base64_encoded_image"}
|
|
Returns: {"success": true, "count": N, "results": [...]}
|
|
"""
|
|
try:
|
|
# Parse request
|
|
data = request.get_json()
|
|
image_base64 = data['image']
|
|
|
|
# Decode image
|
|
image_bytes = base64.b64decode(image_base64)
|
|
image = Image.open(BytesIO(image_bytes))
|
|
image_np = np.array(image)
|
|
|
|
# Run OCR with PP-OCRv5
|
|
result = model.predict(image_np)
|
|
|
|
# Format results
|
|
formatted_results = []
|
|
|
|
if result and 'dt_polys' in result[0] and 'rec_text' in result[0]:
|
|
dt_polys = result[0]['dt_polys']
|
|
rec_texts = result[0]['rec_text']
|
|
rec_scores = result[0]['rec_score']
|
|
|
|
for i in range(len(dt_polys)):
|
|
box = dt_polys[i].tolist() # Convert to list
|
|
text = rec_texts[i]
|
|
confidence = float(rec_scores[i])
|
|
|
|
formatted_results.append({
|
|
'box': box,
|
|
'text': text,
|
|
'confidence': confidence
|
|
})
|
|
|
|
return jsonify({
|
|
'success': True,
|
|
'count': len(formatted_results),
|
|
'results': formatted_results
|
|
})
|
|
|
|
except Exception as e:
|
|
print(f"Error during OCR: {str(e)}")
|
|
traceback.print_exc()
|
|
return jsonify({
|
|
'success': False,
|
|
'error': str(e)
|
|
}), 500
|
|
|
|
if __name__ == '__main__':
|
|
print("Starting PP-OCRv5 server on port 5555...")
|
|
print("Model: PP-OCRv5_server")
|
|
print("Version: 3.3.0")
|
|
app.run(host='0.0.0.0', port=5555, debug=False)
|