feat: add perspective correction code but not working

mv-and-ip/car_plate.py

@@ -118,6 +118,72 @@ def _analyse_car_plate_connection(
     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.
@@ -136,10 +202,11 @@ def extract_car_plate(img: cv.typing.MatLike) -> typing.Optional[cv.typing.MatLi
         # 连通域分析，筛选最符合车牌长宽比的区域作为车牌
         candidate = _analyse_car_plate_connection(mask)
         # 找到任意一个就退出
-        if candidate is not None: break
+        if candidate is not None:
+            break
 
     if candidate is None:
-        logging.error('Can not find any car plate.')
+        logging.error("Can not find any car plate.")
         return None
 
     # 稍微扩边获取最终车牌区域
@@ -149,13 +216,13 @@ def extract_car_plate(img: cv.typing.MatLike) -> typing.Optional[cv.typing.MatLi
     y1 = max(candidate.y - pad, 0)
     x2 = min(candidate.x + candidate.w + pad, w_img)
     y2 = min(candidate.y + candidate.h + pad, h_img)
-    logging.info(f'车牌区域: x={x1}, y={y1}, w={x2 - x1}, h={y2 - y1}')
+    logging.info(f"车牌区域: x={x1}, y={y1}, w={x2 - x1}, h={y2 - y1}")
 
     # # 在原图上标记（仅供调试）
     # debug = img.copy()
     # cv.rectangle(debug, (x1, y1), (x2, y2), (0, 255, 0), 3)
     # cv.imwrite('./debug_detected.jpg', debug)
-    
+
     # 二值化：文字/边缘 → 黑色，背景 → 白色
     gray = cv.cvtColor(img[y1:y2, x1:x2], cv.COLOR_BGR2GRAY)
 
@@ -171,7 +238,29 @@ def extract_car_plate(img: cv.typing.MatLike) -> typing.Optional[cv.typing.MatLi
     kernel_denoise = cv.getStructuringElement(cv.MORPH_RECT, (2, 2))
     binary = cv.morphologyEx(binary, cv.MORPH_OPEN, kernel_denoise)
 
-    #return binary
+    # 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
     # cv.imwrite('./plate_binary.png', binary)
     # print("二值化结果已保存: plate_binary.png")