91 lines
3.0 KiB
Python
91 lines
3.0 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
|
|
import cv2 # Import von OpenCV
|
|
|
|
app = Flask(__name__)
|
|
def preprocess_image(image):
|
|
# Konvertierung zu Graustufen
|
|
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
|
|
|
|
# Kontrastverstärkung
|
|
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8))
|
|
enhanced = clahe.apply(gray)
|
|
|
|
# Rauschreduzierung
|
|
denoised = cv2.fastNlMeansDenoising(enhanced)
|
|
|
|
# Binarisierung
|
|
_, binary = cv2.threshold(denoised, 127, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
|
|
|
|
return binary
|
|
|
|
@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 = preprocess_image(image)
|
|
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
|
|
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)))
|
|
|
|
# Initialisieren Sie PaddleOCR innerhalb des Handlers
|
|
ocr = PaddleOCR(use_angle_cls=True, lang='en') # Initialisierung innerhalb des Handlers
|
|
|
|
result = ocr.ocr(image, rec=True, cls=True)
|
|
|
|
# Extrahieren der Texte und Konfidenzwerte
|
|
extracted_results = []
|
|
for item in result[0]:
|
|
box = item[0] # Die Koordinaten der Textbox
|
|
text = item[1][0] # Der erkannte Text
|
|
confidence = item[1][1] # Der Konfidenzwert
|
|
extracted_results.append({
|
|
'box': box,
|
|
'text': text,
|
|
'confidence': confidence
|
|
})
|
|
|
|
return jsonify(extracted_results)
|
|
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)
|