mirror of
https://github.com/serty2005/rmser.git
synced 2026-02-04 19:02:33 -06:00
97 lines
3.1 KiB
Python
97 lines
3.1 KiB
Python
import cv2
|
||
import numpy as np
|
||
import logging
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
def order_points(pts):
|
||
rect = np.zeros((4, 2), dtype="float32")
|
||
s = pts.sum(axis=1)
|
||
rect[0] = pts[np.argmin(s)]
|
||
rect[2] = pts[np.argmax(s)]
|
||
diff = np.diff(pts, axis=1)
|
||
rect[1] = pts[np.argmin(diff)]
|
||
rect[3] = pts[np.argmax(diff)]
|
||
return rect
|
||
|
||
def four_point_transform(image, pts):
|
||
rect = order_points(pts)
|
||
(tl, tr, br, bl) = rect
|
||
|
||
widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
|
||
widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
|
||
maxWidth = max(int(widthA), int(widthB))
|
||
|
||
heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
|
||
heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
|
||
maxHeight = max(int(heightA), int(heightB))
|
||
|
||
dst = np.array([
|
||
[0, 0],
|
||
[maxWidth - 1, 0],
|
||
[maxWidth - 1, maxHeight - 1],
|
||
[0, maxHeight - 1]], dtype="float32")
|
||
|
||
M = cv2.getPerspectiveTransform(rect, dst)
|
||
warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
|
||
return warped
|
||
|
||
def preprocess_image(image_bytes: bytes) -> np.ndarray:
|
||
"""
|
||
Возвращает БИНАРНОЕ (Ч/Б) изображение для Tesseract.
|
||
"""
|
||
nparr = np.frombuffer(image_bytes, np.uint8)
|
||
image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
|
||
|
||
if image is None:
|
||
raise ValueError("Could not decode image")
|
||
|
||
# Ресайз для поиска контуров
|
||
ratio = image.shape[0] / 500.0
|
||
orig = image.copy()
|
||
image_small = cv2.resize(image, (int(image.shape[1] / ratio), 500))
|
||
|
||
gray = cv2.cvtColor(image_small, cv2.COLOR_BGR2GRAY)
|
||
gray = cv2.GaussianBlur(gray, (5, 5), 0)
|
||
edged = cv2.Canny(gray, 75, 200)
|
||
|
||
cnts, _ = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
|
||
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:5]
|
||
|
||
screenCnt = None
|
||
found = False
|
||
|
||
for c in cnts:
|
||
peri = cv2.arcLength(c, True)
|
||
approx = cv2.approxPolyDP(c, 0.02 * peri, True)
|
||
if len(approx) == 4:
|
||
screenCnt = approx
|
||
found = True
|
||
break
|
||
|
||
# Изображение, с которым будем работать дальше
|
||
target_img = None
|
||
|
||
if found:
|
||
logger.info("Receipt contour found (Tesseract mode).")
|
||
target_img = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)
|
||
else:
|
||
logger.warning("Receipt contour NOT found. Using full image.")
|
||
target_img = orig
|
||
|
||
# --- Подготовка для Tesseract (Бинаризация) ---
|
||
# Переводим в Gray
|
||
gray_final = cv2.cvtColor(target_img, cv2.COLOR_BGR2GRAY)
|
||
|
||
# Адаптивный порог (превращаем в чисто черное и белое)
|
||
# block_size=11, C=2 - классические параметры для текста
|
||
thresh = cv2.adaptiveThreshold(
|
||
gray_final, 255,
|
||
cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
|
||
cv2.THRESH_BINARY, 11, 2
|
||
)
|
||
|
||
# Немного убираем шум
|
||
# thresh = cv2.medianBlur(thresh, 3)
|
||
|
||
return thresh |