revoke: revoke persepctive correction code and fix yellow car plate issue
This commit is contained in:
1
mv-and-ip/.gitignore
vendored
1
mv-and-ip/.gitignore
vendored
@@ -4,6 +4,7 @@
|
||||
|
||||
# All image files
|
||||
*.jpg
|
||||
*.jpeg
|
||||
*.png
|
||||
*.webp
|
||||
|
||||
|
||||
@@ -49,21 +49,30 @@ def _uniform_car_plate(img: cv.typing.MatLike) -> cv.typing.MatLike:
|
||||
class CarPlateHsvBoundary:
|
||||
lower_bound: cv.typing.MatLike
|
||||
upper_bound: cv.typing.MatLike
|
||||
need_revert: bool
|
||||
"""是否取反黑白颜色，因为蓝牌和黄牌的操作正好是反的"""
|
||||
|
||||
|
||||
CAR_PLATE_HSV_BOUNDARIES: tuple[CarPlateHsvBoundary, ...] = (
|
||||
# 中国蓝牌 HSV 范围
|
||||
CarPlateHsvBoundary(np.array([100, 80, 60]), np.array([130, 255, 255])),
|
||||
CarPlateHsvBoundary(np.array([100, 80, 60]), np.array([130, 255, 255]), True),
|
||||
# 中国绿牌 HSV 范围
|
||||
CarPlateHsvBoundary(np.array([35, 43, 46]), np.array([99, 255, 255])),
|
||||
CarPlateHsvBoundary(np.array([35, 43, 46]), np.array([99, 255, 255]), False),
|
||||
# 中国黄牌 HSV 范围
|
||||
CarPlateHsvBoundary(np.array([32, 43, 46]), np.array([68, 255, 255])),
|
||||
CarPlateHsvBoundary(np.array([16, 43, 46]), np.array([34, 255, 255]), False),
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class CarPlateMask:
|
||||
mask: cv.typing.MatLike
|
||||
need_revert: bool
|
||||
"""是否对颜色取反，与CarPlateHsvBoundary中的同名字段含义一致"""
|
||||
|
||||
|
||||
def _batchly_mask_car_plate(
|
||||
hsv: cv.typing.MatLike,
|
||||
) -> typing.Iterator[cv.typing.MatLike]:
|
||||
) -> typing.Iterator[CarPlateMask]:
|
||||
""" """
|
||||
for boundary in CAR_PLATE_HSV_BOUNDARIES:
|
||||
# 以给定HSV范围检测符合该颜色的位置
|
||||
@@ -76,7 +85,7 @@ def _batchly_mask_car_plate(
|
||||
mask = cv.morphologyEx(mask, cv.MORPH_OPEN, kernel_open)
|
||||
|
||||
# Return value
|
||||
yield mask
|
||||
yield CarPlateMask(mask, boundary.need_revert)
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -85,6 +94,8 @@ class CarPlateRegion:
|
||||
y: int
|
||||
w: int
|
||||
h: int
|
||||
need_revert: bool
|
||||
"""是否对颜色取反，与CarPlateHsvBoundary中的同名字段含义一致"""
|
||||
|
||||
|
||||
MIN_AREA: float = 3000
|
||||
@@ -94,10 +105,12 @@ BEST_ASPECT_RATIO: float = 3.5
|
||||
|
||||
|
||||
def _analyse_car_plate_connection(
|
||||
mask: cv.typing.MatLike,
|
||||
mask: CarPlateMask,
|
||||
) -> typing.Optional[CarPlateRegion]:
|
||||
# 连通域分析，筛选最符合车牌长宽比的区域
|
||||
num_labels, labels, stats, _ = cv.connectedComponentsWithStats(mask, connectivity=8)
|
||||
num_labels, labels, stats, _ = cv.connectedComponentsWithStats(
|
||||
mask.mask, connectivity=8
|
||||
)
|
||||
|
||||
best: typing.Optional[CarPlateRegion] = None
|
||||
best_score = 0
|
||||
@@ -113,77 +126,11 @@ def _analyse_car_plate_connection(
|
||||
score = area * (1 - abs(ratio - BEST_ASPECT_RATIO) / BEST_ASPECT_RATIO)
|
||||
if score > best_score:
|
||||
best_score = score
|
||||
best = CarPlateRegion(x, y, w, h)
|
||||
best = CarPlateRegion(x, y, w, h, mask.need_revert)
|
||||
|
||||
return best
|
||||
|
||||
|
||||
@dataclass
|
||||
class PerspectiveData:
|
||||
top_left: tuple[int, int]
|
||||
top_right: tuple[int, int]
|
||||
bottom_left: tuple[int, int]
|
||||
bottom_right: tuple[int, int]
|
||||
|
||||
new_width: int
|
||||
new_height: int
|
||||
|
||||
|
||||
def _extract_perspective_data(
|
||||
gray: cv.typing.MatLike,
|
||||
) -> typing.Optional[PerspectiveData]:
|
||||
""" """
|
||||
# Histogram balance to increase contrast
|
||||
hist_gray = cv.equalizeHist(gray)
|
||||
|
||||
# Apply Gaussian blur to reduce noise
|
||||
blurred = cv.GaussianBlur(hist_gray, (5, 5), 0)
|
||||
|
||||
# Edge detection using Canny
|
||||
edges = cv.Canny(blurred, 50, 150)
|
||||
|
||||
# Find contours
|
||||
contours, _ = cv.findContours(edges, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
|
||||
if not contours:
|
||||
return None
|
||||
# Find the largest one because all image is car plate
|
||||
max_area_contour = max(contours, key=lambda contour: cv.contourArea(contour))
|
||||
|
||||
# Approximate the contour
|
||||
peri = cv.arcLength(max_area_contour, True)
|
||||
approx = cv.approxPolyDP(max_area_contour, 0.02 * peri, True)
|
||||
if len(approx) != 4:
|
||||
return None
|
||||
|
||||
# Perspective transformation to get front view
|
||||
# Order points: top-left, top-right, bottom-right, bottom-left
|
||||
pts = approx.reshape(4, 2)
|
||||
rect = np.zeros((4, 2), dtype="float32")
|
||||
|
||||
# Sum and difference of coordinates to find corners
|
||||
s = pts.sum(axis=1)
|
||||
top_left = pts[np.argmin(s)] # Top-left has smallest sum
|
||||
bottom_right = pts[np.argmax(s)] # Bottom-right has largest sum
|
||||
|
||||
diff = np.diff(pts, axis=1)
|
||||
top_right = pts[np.argmin(diff)] # Top-right has smallest difference
|
||||
bottom_left = pts[np.argmax(diff)] # Bottom-left has largest difference
|
||||
|
||||
# Calculate width and height of new image
|
||||
width_a = np.linalg.norm(rect[0] - rect[1])
|
||||
width_b = np.linalg.norm(rect[2] - rect[3])
|
||||
max_width = max(int(width_a), int(width_b))
|
||||
|
||||
height_a = np.linalg.norm(rect[0] - rect[3])
|
||||
height_b = np.linalg.norm(rect[1] - rect[2])
|
||||
max_height = max(int(height_a), int(height_b))
|
||||
|
||||
# Return value
|
||||
return PerspectiveData(
|
||||
top_left, top_right, bottom_left, bottom_right, max_width, max_height
|
||||
)
|
||||
|
||||
|
||||
def extract_car_plate(img: cv.typing.MatLike) -> typing.Optional[cv.typing.MatLike]:
|
||||
"""
|
||||
Extract the car plate part from given image.
|
||||
@@ -232,39 +179,20 @@ def extract_car_plate(img: cv.typing.MatLike) -> typing.Optional[cv.typing.MatLi
|
||||
# Otsu 自动阈值，得到白字黑底，再取反 → 黑字白底
|
||||
_, binary_otsu = cv.threshold(blurred, 0, 255, cv.THRESH_BINARY + cv.THRESH_OTSU)
|
||||
# 反转：字符变黑，背景变白
|
||||
binary = cv.bitwise_not(binary_otsu)
|
||||
if candidate.need_revert:
|
||||
binary = cv.bitwise_not(binary_otsu)
|
||||
else:
|
||||
binary = binary_otsu
|
||||
|
||||
# 去除小噪点（开运算）
|
||||
kernel_denoise = cv.getStructuringElement(cv.MORPH_RECT, (2, 2))
|
||||
binary = cv.morphologyEx(binary, cv.MORPH_OPEN, kernel_denoise)
|
||||
|
||||
# 尝试获取视角矫正数据
|
||||
perspective_data = _extract_perspective_data(gray)
|
||||
if perspective_data is None:
|
||||
logging.warning(f'Can not fetch perspective data. The output image has no perspective correction.')
|
||||
return binary
|
||||
|
||||
# 执行视角矫正
|
||||
perspective_src = np.array([
|
||||
list(perspective_data.top_left),
|
||||
list(perspective_data.top_right),
|
||||
list(perspective_data.bottom_right),
|
||||
list(perspective_data.bottom_left)
|
||||
], dtype="float32")
|
||||
perspective_dst = np.array([
|
||||
[0, 0],
|
||||
[perspective_data.new_width - 1, 0],
|
||||
[perspective_data.new_width - 1, perspective_data.new_height - 1],
|
||||
[0, perspective_data.new_height - 1]
|
||||
], dtype="float32")
|
||||
M = cv.getPerspectiveTransform(perspective_src, perspective_dst)
|
||||
warped = cv.warpPerspective(binary, M, (perspective_data.new_width, perspective_data.new_height))
|
||||
|
||||
return warped
|
||||
return binary
|
||||
# cv.imwrite('./plate_binary.png', binary)
|
||||
# print("二值化结果已保存: plate_binary.png")
|
||||
|
||||
# ── 4. 叠加边框轮廓（细化文字边缘，参考效果图）─────────────────────
|
||||
# 叠加边框轮廓（细化文字边缘，参考效果图）
|
||||
# Canny 边缘叠加让效果更接近参考图
|
||||
edges = cv.Canny(blurred, 40, 120)
|
||||
edges_inv = cv.bitwise_not(edges) # 边缘→黑色
|
||||
|
||||
Reference in New Issue
Block a user