vocab-backend/ocr_server.py

61 lines
2.2 KiB
Python

from flask import Flask, request, jsonify
from paddleocr import PaddleOCR
import base64
from PIL import Image
from io import BytesIO
import traceback
import numpy as np # Importieren von numpy
app = Flask(__name__)
ocr = PaddleOCR(use_angle_cls=True, lang='en') # Passen Sie die Sprache nach Bedarf an
@app.route('/ocr', methods=['POST'])
def ocr_endpoint():
try:
if not request.is_json:
return jsonify({'error': 'Content-Type must be application/json'}), 400
data = request.get_json()
if not data or 'image' not in data:
return jsonify({'error': 'No image provided'}), 400
image_b64 = data['image']
if not image_b64:
return jsonify({'error': 'Empty image data'}), 400
try:
image_data = base64.b64decode(image_b64)
except Exception as decode_err:
return jsonify({'error': 'Base64 decode error', 'details': str(decode_err)}), 400
try:
image = Image.open(BytesIO(image_data)).convert('RGB')
image = np.array(image) # Konvertieren zu numpy.ndarray
except Exception as img_err:
return jsonify({'error': 'Invalid image data', 'details': str(img_err)}), 400
# Optional: Bildgröße anpassen, falls erforderlich
# PaddleOCR kann große Bilder verarbeiten, aber zur Effizienz können Sie eine maximale Größe setzen
max_width = 1920
max_height = 1080
height, width, _ = image.shape
if width > max_width or height > max_height:
aspect_ratio = width / height
if aspect_ratio > 1:
new_width = max_width
new_height = int(max_width / aspect_ratio)
else:
new_height = max_height
new_width = int(max_height * aspect_ratio)
image = np.array(Image.fromarray(image).resize((new_width, new_height)))
result = ocr.ocr(image, rec=True, cls=True)
return jsonify(result)
except Exception as e:
traceback.print_exc()
return jsonify({'error': str(e)}), 500
if __name__ == '__main__':
app.run(host='0.0.0.0', port=5000, debug=True)