ADD file via upload

advanced/license_plate_recog/image_operations.py

@@ -0,0 +1,160 @@
+import cv2
+import os
+import numpy as np
+import pytesseract
+
+
+def locate_license_plate(image_path):
+    if not os.path.isfile(image_path):
+        print(f"Error: File '{image_path}' does not exist.")
+        return None
+
+    """
+    根据输入的图像路径，定位蓝色车牌并返回裁剪出的车牌区域
+    """
+    # 读取图像
+    car = cv2.imread(image_path, 1)
+
+    if car is None:
+        print(f"Error: Unable to read image '{image_path}'")
+        return None
+
+    # 定义蓝色所对应的色彩空间范围
+    lower_blue = np.array([100, 110, 110])
+    upper_blue = np.array([130, 255, 255])
+
+    # 将图像转换到HSV颜色空间
+    hsv = cv2.cvtColor(car, cv2.COLOR_BGR2HSV)
+
+    # 获取蓝色区域的掩模
+    mask_blue = cv2.inRange(hsv, lower_blue, upper_blue)
+
+    # 将掩模转换为灰度图像
+    mask = mask_blue
+
+    # 形态学处理，开运算和闭运算
+    matrix = np.ones((20, 20), np.uint8)
+    mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, matrix)
+    mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, matrix)
+
+    # 二值化
+    ret, mask = cv2.threshold(mask, 0, 255, cv2.THRESH_BINARY)
+
+    # 查找轮廓
+    contours, hierarchy = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+
+    # 寻找最大轮廓并定位车牌
+    max_area = 0
+    best_contour = None
+    for contour in contours:
+        area = cv2.contourArea(contour)
+        if area > max_area:
+            max_area = area
+            best_contour = contour
+
+    # 获取定位车牌的外接矩形框
+    rect = cv2.minAreaRect(best_contour)
+    box = cv2.boxPoints(rect)
+    box = np.int32(box)
+
+    # 获取旋转矩阵
+    angle = rect[2]
+    flag = 0
+    print(angle)
+    if angle < -45:
+        angle += 90
+        flag = 1
+    if angle > 45:
+        angle -= 90
+        flag = 1
+        print(angle)
+    center = (rect[0][0], rect[0][1])
+    size = (int(rect[1][0]), int(rect[1][1]))
+    M = cv2.getRotationMatrix2D(center, angle, 1.0)
+
+    # 旋转图像
+    height, width = car.shape[:2]
+    rotated = cv2.warpAffine(car, M, (width, height))
+
+    # 获取旋转后矩形框的坐标
+    if flag == 0:
+        box = cv2.boxPoints(((center[0], center[1]), (size[0], size[1]), 0.0))
+        box = np.int32(box)
+
+    # 裁剪车牌区域
+    xs = [box[0, 0], box[1, 0], box[2, 0], box[3, 0]]
+    ys = [box[0, 1], box[1, 1], box[2, 1], box[3, 1]]
+    x1, x2 = min(xs), max(xs)
+    y1, y2 = min(ys), max(ys)
+    ROI_plate = rotated[y1:y2, x1:x2]
+
+    return ROI_plate
+
+
+def preprocess_image_for_ocr(image):
+    """
+    预处理图像以提高 OCR 识别率
+    """
+    # 去除左右上下各3个像素的边框
+    height, width = image.shape[:2]
+    image = image[3:height - 3, 3:width - 3]
+
+    # 调整图像大小到 165x40
+    image = cv2.resize(image, (165, 40), interpolation=cv2.INTER_AREA)
+
+    # 转换为灰度图像
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+    # 二值化
+    _, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+
+    # 去噪
+    denoised = cv2.medianBlur(binary, 3)
+
+    return denoised
+
+
+def find_split_line(image):
+    """
+    在宽度15-30像素之间查找分割线
+    """
+    height, width = image.shape
+    column_sums = np.sum(image[3:height - 3, 15:30], axis=0)  # 忽略顶部和底部的像素
+
+    zero_columns = np.where(column_sums == 0)[0]  # 找到像素和为0的列
+    if len(zero_columns) == 0:
+        # 如果没有找到和为0的列，返回默认分割线为22
+        split_line = 22
+    else:
+        # 计算零列的中值作为分割线
+        split_line = int(np.median(zero_columns)) + 15  # 加上偏移量15
+    print(split_line)
+    return split_line
+
+
+def recognize_characters(image):
+    """
+    使用OCR技术识别车牌上的字符
+    """
+    preprocessed_image = preprocess_image_for_ocr(image)
+
+    # 找到分割线
+    split_line = find_split_line(preprocessed_image)
+
+    # 切割图像为两部分
+    part1 = preprocessed_image[:, :split_line]  # 宽度0-split_line部分
+    part2 = preprocessed_image[:, split_line:]  # 剩余部分
+
+    # 调用 Tesseract OCR 识别宽度0-24部分
+    custom_config_chi_sim = r'--oem 3 --psm 6 -l chi_sim'
+    result_chi_sim = pytesseract.image_to_string(part1, config=custom_config_chi_sim)
+
+    # 调用 Tesseract OCR 识别剩余部分
+    custom_config_default = r'--oem 3 --psm 6'
+    result_default = pytesseract.image_to_string(part2, config=custom_config_default)
+
+    # 合并两个部分的识别结果
+    recognized_characters = result_chi_sim.strip() + result_default.strip()
+
+    return recognized_characters
+