Anpassungen und Reduzierung auf OCR
This commit is contained in:
273
ocr_server.py
273
ocr_server.py
@@ -1,17 +1,98 @@
|
||||
from flask import Flask, request, jsonify
|
||||
from flask import Flask, request, jsonify, send_file
|
||||
from paddleocr import PaddleOCR
|
||||
import base64
|
||||
from PIL import Image
|
||||
from io import BytesIO
|
||||
import traceback
|
||||
import numpy as np # Importieren von numpy
|
||||
import numpy as np
|
||||
import cv2
|
||||
import logging
|
||||
import os
|
||||
import uuid
|
||||
import datetime
|
||||
from app_factory import app
|
||||
# from deck_endpoints import deck_bp # Importieren des Blueprints
|
||||
|
||||
app = Flask(__name__)
|
||||
ocr = PaddleOCR(use_angle_cls=True, lang='en') # Passen Sie die Sprache nach Bedarf an
|
||||
logging.basicConfig(
|
||||
level=logging.DEBUG,
|
||||
format='%(asctime)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@app.route('/ocr', methods=['POST'])
|
||||
# app = Flask(__name__)
|
||||
# app.register_blueprint(deck_bp) # Registrieren des Blueprints
|
||||
|
||||
def get_dir_name():
|
||||
timestamp = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')
|
||||
unique_id = str(uuid.uuid4())[:8]
|
||||
return f"{timestamp}_{unique_id}"
|
||||
|
||||
def create_debug_directory(dir_name):
|
||||
"""Erstellt ein eindeutiges Verzeichnis für Debug-Bilder"""
|
||||
base_dir = 'debug_images'
|
||||
timestamp = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')
|
||||
unique_id = str(uuid.uuid4())[:8]
|
||||
full_path = os.path.join(base_dir, dir_name)
|
||||
|
||||
# Erstelle Hauptverzeichnis falls nicht vorhanden
|
||||
if not os.path.exists(base_dir):
|
||||
os.makedirs(base_dir)
|
||||
|
||||
# Erstelle spezifisches Verzeichnis für diesen Durchlauf
|
||||
os.makedirs(full_path)
|
||||
|
||||
return full_path
|
||||
|
||||
def preprocess_image(image, debug_dir):
|
||||
"""
|
||||
Verarbeitet das Bild und speichert Zwischenergebnisse im angegebenen Verzeichnis,
|
||||
einschließlich einer komprimierten JPG-Version und eines Thumbnails.
|
||||
"""
|
||||
try:
|
||||
# Umwandlung in Graustufen
|
||||
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
|
||||
# Anwendung von CLAHE zur Kontrastverbesserung
|
||||
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8))
|
||||
enhanced = clahe.apply(gray)
|
||||
# Rauschunterdrückung
|
||||
denoised = cv2.fastNlMeansDenoising(enhanced)
|
||||
# Optional: Binärschwellenwert (auskommentiert)
|
||||
# _, binary = cv2.threshold(denoised, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
|
||||
|
||||
# Speichern der Zwischenergebnisse im spezifischen Verzeichnis
|
||||
cv2.imwrite(os.path.join(debug_dir, 'gray.png'), gray)
|
||||
cv2.imwrite(os.path.join(debug_dir, 'enhanced.png'), enhanced)
|
||||
cv2.imwrite(os.path.join(debug_dir, 'denoised.png'), denoised)
|
||||
# cv2.imwrite(os.path.join(debug_dir, 'binary.png'), binary)
|
||||
|
||||
# Speichern der komprimierten JPG-Version des Originalbildes
|
||||
compressed_jpg_path = os.path.join(debug_dir, 'original_compressed.jpg')
|
||||
original_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
|
||||
cv2.imwrite(compressed_jpg_path, original_bgr, [int(cv2.IMWRITE_JPEG_QUALITY), 80]) # Qualität auf 80 setzen
|
||||
logger.info(f"Komprimiertes Original JPG gespeichert: {compressed_jpg_path}")
|
||||
|
||||
# Erstellen und Speichern des Thumbnails
|
||||
thumbnail_path = os.path.join(debug_dir, 'thumbnail.jpg')
|
||||
image_pil = Image.fromarray(denoised)
|
||||
image_pil.thumbnail((128, 128)) # Thumbnail-Größe auf 128x128 Pixel setzen
|
||||
image_pil.save(thumbnail_path, 'JPEG')
|
||||
logger.info(f"Thumbnail gespeichert: {thumbnail_path}")
|
||||
|
||||
logger.info(f"Debug images saved in: {debug_dir}")
|
||||
return denoised
|
||||
except Exception as e:
|
||||
logger.error(f"Preprocessing error: {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@app.route('/api/ocr', methods=['POST'])
|
||||
def ocr_endpoint():
|
||||
try:
|
||||
# Erstelle eindeutiges Debug-Verzeichnis für diesen Request
|
||||
dir_name = get_dir_name()
|
||||
debug_dir = create_debug_directory(dir_name)
|
||||
logger.info(f"Created debug directory: {debug_dir}")
|
||||
|
||||
if not request.is_json:
|
||||
return jsonify({'error': 'Content-Type must be application/json'}), 400
|
||||
|
||||
@@ -20,41 +101,167 @@ def ocr_endpoint():
|
||||
return jsonify({'error': 'No image provided'}), 400
|
||||
|
||||
image_b64 = data['image']
|
||||
if not image_b64:
|
||||
return jsonify({'error': 'Empty image data'}), 400
|
||||
|
||||
# Base64 Dekodierung
|
||||
try:
|
||||
image_data = base64.b64decode(image_b64)
|
||||
except Exception as decode_err:
|
||||
return jsonify({'error': 'Base64 decode error', 'details': str(decode_err)}), 400
|
||||
|
||||
logger.error(f"Base64 decode error: {str(decode_err)}")
|
||||
return jsonify({'error': 'Base64 decode error'}), 400
|
||||
|
||||
# Bildverarbeitung
|
||||
try:
|
||||
image = Image.open(BytesIO(image_data)).convert('RGB')
|
||||
image = np.array(image) # Konvertieren zu numpy.ndarray
|
||||
image = np.array(image)
|
||||
logger.info(f"Image loaded successfully. Shape: {image.shape}")
|
||||
|
||||
# Originalbild speichern
|
||||
cv2.imwrite(os.path.join(debug_dir, 'original.png'),
|
||||
cv2.cvtColor(image, cv2.COLOR_RGB2BGR))
|
||||
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)
|
||||
logger.error(f"Image processing error: {str(img_err)}")
|
||||
return jsonify({'error': 'Invalid image data'}), 400
|
||||
|
||||
# Bildvorverarbeitung
|
||||
processed_image = preprocess_image(image, debug_dir)
|
||||
logger.info("Preprocessing completed")
|
||||
|
||||
# PaddleOCR Konfiguration
|
||||
ocr = PaddleOCR(
|
||||
use_angle_cls=True,
|
||||
lang='en',
|
||||
det_db_thresh=0.3,
|
||||
det_db_box_thresh=0.3,
|
||||
det_db_unclip_ratio=2.0,
|
||||
rec_char_type='en',
|
||||
det_limit_side_len=960,
|
||||
det_limit_type='max',
|
||||
use_dilation=True,
|
||||
det_db_score_mode='fast',
|
||||
show_log=True
|
||||
)
|
||||
|
||||
# OCR durchführen
|
||||
try:
|
||||
result = ocr.ocr(processed_image, rec=True, cls=True)
|
||||
|
||||
# Debug-Informationen in Datei speichern
|
||||
with open(os.path.join(debug_dir, 'ocr_results.txt'), 'w') as f:
|
||||
f.write(f"Raw OCR result:\n{result}\n\n")
|
||||
|
||||
if not result:
|
||||
logger.warning("No results returned from OCR")
|
||||
return jsonify({
|
||||
'warning': 'No text detected',
|
||||
'debug_dir': debug_dir
|
||||
}), 200
|
||||
|
||||
if not result[0]:
|
||||
logger.warning("Empty results list from OCR")
|
||||
return jsonify({
|
||||
'warning': 'Empty results list',
|
||||
'debug_dir': debug_dir
|
||||
}), 200
|
||||
|
||||
# Ergebnisse verarbeiten
|
||||
extracted_results = []
|
||||
for idx, item in enumerate(result[0]):
|
||||
try:
|
||||
box = item[0]
|
||||
text = item[1][0] if item[1] else ''
|
||||
confidence = float(item[1][1]) if item[1] and len(item[1]) > 1 else 0.0
|
||||
|
||||
extracted_results.append({
|
||||
'box': box,
|
||||
'text': text,
|
||||
'confidence': confidence,
|
||||
'name': dir_name
|
||||
})
|
||||
except Exception as proc_err:
|
||||
logger.error(f"Error processing result {idx}: {str(proc_err)}")
|
||||
|
||||
# Statistiken in Debug-Datei speichern
|
||||
with open(os.path.join(debug_dir, 'statistics.txt'), 'w') as f:
|
||||
f.write(f"Total results: {len(extracted_results)}\n")
|
||||
if extracted_results:
|
||||
avg_confidence = np.mean([r['confidence'] for r in extracted_results])
|
||||
f.write(f"Average confidence: {avg_confidence}\n")
|
||||
f.write("\nDetailed results:\n")
|
||||
for idx, result in enumerate(extracted_results):
|
||||
f.write(f"Result {idx+1}:\n")
|
||||
f.write(f"Text: {result['text']}\n")
|
||||
f.write(f"Confidence: {result['confidence']}\n")
|
||||
f.write(f"Name: {dir_name}\n")
|
||||
f.write(f"Box coordinates: {result['box']}\n\n")
|
||||
|
||||
return jsonify({
|
||||
'status': 'success',
|
||||
'results': extracted_results,
|
||||
})
|
||||
|
||||
except Exception as ocr_err:
|
||||
logger.error(f"OCR processing error: {str(ocr_err)}")
|
||||
logger.error(traceback.format_exc())
|
||||
return jsonify({
|
||||
'error': 'OCR processing failed',
|
||||
'details': str(ocr_err),
|
||||
'debug_dir': debug_dir
|
||||
}), 500
|
||||
|
||||
except Exception as e:
|
||||
traceback.print_exc()
|
||||
return jsonify({'error': str(e)}), 500
|
||||
logger.error(f"Unexpected error: {str(e)}")
|
||||
logger.error(traceback.format_exc())
|
||||
return jsonify({
|
||||
'error': 'Internal server error',
|
||||
'debug_dir': debug_dir if 'debug_dir' in locals() else None
|
||||
}), 500
|
||||
|
||||
@app.route('/api/debug_image/<name>/<filename>', methods=['GET'])
|
||||
def get_debug_image(name, filename):
|
||||
"""
|
||||
Gibt das angeforderte Bild unter 'debug_images/[name]/[filename]' direkt zurück.
|
||||
"""
|
||||
try:
|
||||
# Sicherheitsmaßnahme: Nur erlaubte Zeichen im Verzeichnisnamen
|
||||
if not all(c.isalnum() or c in ('_', '-') for c in name):
|
||||
logger.warning(f"Ungültiger Verzeichnisname angefordert: {name}")
|
||||
return jsonify({'error': 'Invalid directory name'}), 400
|
||||
|
||||
# Sicherheitsmaßnahme: Nur erlaubte Zeichen im Dateinamen
|
||||
if not all(c.isalnum() or c in ('_', '-', '.',) for c in filename):
|
||||
logger.warning(f"Ungültiger Dateiname angefordert: {filename}")
|
||||
return jsonify({'error': 'Invalid file name'}), 400
|
||||
|
||||
# Vollständigen Pfad zum Bild erstellen
|
||||
image_path = os.path.join('debug_images', name, filename)
|
||||
|
||||
# Überprüfen, ob die Datei existiert
|
||||
if not os.path.isfile(image_path):
|
||||
logger.warning(f"Bild nicht gefunden: {image_path}")
|
||||
return jsonify({'error': 'Image not found'}), 404
|
||||
|
||||
# Bestimmen des MIME-Typs basierend auf der Dateiendung
|
||||
mime_type = 'image/png' # Standard-MIME-Typ
|
||||
if filename.lower().endswith('.jpg') or filename.lower().endswith('.jpeg'):
|
||||
mime_type = 'image/jpeg'
|
||||
elif filename.lower().endswith('.gif'):
|
||||
mime_type = 'image/gif'
|
||||
elif filename.lower().endswith('.bmp'):
|
||||
mime_type = 'image/bmp'
|
||||
elif filename.lower().endswith('.tiff') or filename.lower().endswith('.tif'):
|
||||
mime_type = 'image/tiff'
|
||||
|
||||
return send_file(
|
||||
image_path,
|
||||
mimetype=mime_type,
|
||||
as_attachment=False
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Fehler beim Abrufen des Bildes '{name}/{filename}': {str(e)}")
|
||||
logger.error(traceback.format_exc())
|
||||
return jsonify({'error': 'Failed to retrieve image'}), 500
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
app.run(host='0.0.0.0', port=5000, debug=True)
|
||||
|
||||
app.run(host='0.0.0.0', port=5000, debug=True)
|
||||
Reference in New Issue
Block a user