44 lines
1.9 KiB
Python
44 lines
1.9 KiB
Python
|
|
import cv2
|
|
import numpy as np
|
|
from typing import List, Dict, Any
|
|
from shapely.geometry import Polygon
|
|
import logging
|
|
|
|
class MaskModule:
|
|
def __init__(self, logger, base_dir):
|
|
self.logger = logger
|
|
self.base_dir = base_dir
|
|
self.logger.log("마스크 모듈 초기화 완료", level=logging.INFO)
|
|
|
|
def create_masks(self, image_path: str, ocr_results: List[Dict], expansion_size: int = 10, blur_size: int = 15, mask_option: str = "basic") -> np.ndarray:
|
|
image = cv2.imread(image_path)
|
|
if image is None:
|
|
self.logger.log(f"이미지를 읽을 수 없습니다: {image_path}", level=logging.ERROR)
|
|
return None
|
|
height, width = image.shape[:2]
|
|
mask = np.zeros((height, width), dtype=np.uint8)
|
|
for i, result in enumerate(ocr_results, 1):
|
|
polygon = result['polygon']
|
|
expanded_poly = self.expand_polygon(polygon, offset=5)
|
|
cv2.fillPoly(mask, [expanded_poly], 255)
|
|
processed_mask = self.process_mask(mask, expansion_size, blur_size)
|
|
return processed_mask
|
|
|
|
def expand_polygon(self, polygon, offset=15):
|
|
poly = Polygon(polygon)
|
|
expanded = poly.buffer(offset)
|
|
if expanded.is_empty:
|
|
return np.array(polygon, dtype=np.int32)
|
|
return np.array(expanded.exterior.coords, dtype=np.int32)
|
|
|
|
def process_mask(self, mask: np.ndarray, expansion_size: int = 5, blur_size: int = 3) -> np.ndarray:
|
|
processed_mask = mask.copy()
|
|
if expansion_size > 0:
|
|
kernel = np.ones((expansion_size, expansion_size), np.uint8)
|
|
processed_mask = cv2.dilate(processed_mask, kernel, iterations=1)
|
|
if blur_size > 0:
|
|
blur_size = blur_size if blur_size % 2 == 1 else blur_size + 1
|
|
processed_mask = cv2.GaussianBlur(processed_mask, (blur_size, blur_size), 0)
|
|
return processed_mask
|
|
|