41 lines
1.5 KiB
Python
Executable File
41 lines
1.5 KiB
Python
Executable File
# /opt/docker/dev/service_finder/backend/app/services/image_processor.py
|
|
import cv2
|
|
import numpy as np
|
|
import logging
|
|
from typing import Optional
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class DocumentImageProcessor:
|
|
""" Saját képtisztító pipeline Robot 3 OCR számára. """
|
|
|
|
@staticmethod
|
|
def process_for_ocr(image_bytes: bytes) -> Optional[bytes]:
|
|
if not image_bytes: return None
|
|
try:
|
|
nparr = np.frombuffer(image_bytes, np.uint8)
|
|
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
|
|
if img is None: return None
|
|
|
|
# 1. Előkészítés (Szürkeárnyalat + Felskálázás)
|
|
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
|
if gray.shape[1] < 1200:
|
|
gray = cv2.resize(gray, None, fx=2.0, fy=2.0, interpolation=cv2.INTER_CUBIC)
|
|
|
|
# 2. Kontraszt dúsítás (CLAHE)
|
|
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
|
|
contrast = clahe.apply(gray)
|
|
|
|
# 3. Adaptív Binarizálás (Fekete-fehér szöveg kiemelés)
|
|
blur = cv2.GaussianBlur(contrast, (3, 3), 0)
|
|
thresh = cv2.adaptiveThreshold(
|
|
blur, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
|
|
cv2.THRESH_BINARY, 11, 2
|
|
)
|
|
|
|
success, encoded_image = cv2.imencode('.png', thresh)
|
|
return encoded_image.tobytes() if success else None
|
|
|
|
except Exception as e:
|
|
logger.error(f"OpenCV Feldolgozási hiba: {e}")
|
|
return None |