import cv2
import numpy as npdef calculate_overlap_percentage(a_image_path, b_image_path):# 读取A组和B组图像a_image = cv2.imread(a_image_path)b_image = cv2.imread(b_image_path)# 将图像从BGR转为HSV色彩空间，便于颜色筛选a_hsv = cv2.cvtColor(a_image, cv2.COLOR_BGR2HSV)b_hsv = cv2.cvtColor(b_image, cv2.COLOR_BGR2HSV)# 设置B组红色的HSV范围lower_red = np.array([0, 100, 100])upper_red = np.array([10, 255, 255])# 提取B组红色区域的掩膜b_red_mask = cv2.inRange(b_hsv, lower_red, upper_red)# 设置A组颜色区域的HSV范围（棕色和绿色）# 棕色的HSV范围lower_brown = np.array([10, 30, 30])upper_brown = np.array([25, 255, 200])# 绿色的HSV范围lower_green = np.array([35, 50, 50])upper_green = np.array([85, 255, 255])# 提取A组棕色和绿色区域的掩膜a_brown_mask = cv2.inRange(a_hsv, lower_brown, upper_brown)a_green_mask = cv2.inRange(a_hsv, lower_green, upper_green)# 合并A组的棕色和绿色区域掩膜a_color_mask = cv2.bitwise_or(a_brown_mask, a_green_mask)# 计算B组红色区域的像素数量b_red_area = cv2.countNonZero(b_red_mask)# 在A组中找到与B组红色区域重合的区域a_overlap = cv2.bitwise_and(a_color_mask, b_red_mask)# 计算A组与B组红色区域重合的像素数量a_overlap_area = cv2.countNonZero(a_overlap)# 计算A组有颜色区域占B组红色区域的百分比overlap_percentage = (a_overlap_area / b_red_area) * 100 if b_red_area != 0 else 0return overlap_percentage# 示例调用
a_image_path = "path_to_a_image.jpg"
b_image_path = "path_to_b_image.jpg"
percentage = calculate_overlap_percentage(a_image_path, b_image_path)
print(f"A组颜色区域占B组红色区域的百分比为: {percentage:.2f}%")
下面查看提取的mask是否正确
# 调整显示图像的大小（设置为目标宽度 600 像素）height, width = b_red_mask.shapetarget_width = 600target_height = int(target_width * height / width)# 使用 cv2.resize 调整图像大小b_red_mask_resized = cv2.resize(b_red_mask, (target_width, target_height))# 显示调整后的B组红色掩膜cv2.imshow("B Red Mask", b_red_mask_resized)cv2.waitKey(0) # 等待按键按下cv2.destroyAllWindows() # 关闭所有窗口下面直接输出图片是户更方便
cv2.imwrite("a_color_mask.png", a_color_mask)
把a组与b组文件夹下的所有对应的图片进行计算，然后输出到一个txt文件
import cv2
import numpy as np
import osdef calculate_overlap_percentage(a_image_path, b_image_path):# 读取A组和B组图像a_image = cv2.imread(a_image_path)b_image = cv2.imread(b_image_path)# 将图像从BGR转为HSV色彩空间，便于颜色筛选a_hsv = cv2.cvtColor(a_image, cv2.COLOR_BGR2HSV)b_hsv = cv2.cvtColor(b_image, cv2.COLOR_BGR2HSV)# 设置B组红色的HSV范围lower_red = np.array([0, 100, 100])upper_red = np.array([10, 255, 255])# 提取B组红色区域的掩膜b_red_mask = cv2.inRange(b_hsv, lower_red, upper_red)# 设置A组颜色区域的HSV范围（棕色和绿色）# 棕色的HSV范围lower_brown = np.array([10, 30, 30])upper_brown = np.array([25, 255, 200])# 绿色的HSV范围lower_green = np.array([35, 50, 50])upper_green = np.array([85, 255, 255])# 提取A组棕色和绿色区域的掩膜a_brown_mask = cv2.inRange(a_hsv, lower_brown, upper_brown)a_green_mask = cv2.inRange(a_hsv, lower_green, upper_green)# 合并A组的棕色和绿色区域掩膜a_color_mask = cv2.bitwise_or(a_brown_mask, a_green_mask)# 计算B组红色区域的像素数量b_red_area = cv2.countNonZero(b_red_mask)# 在A组中找到与B组红色区域重合的区域a_overlap = cv2.bitwise_and(a_color_mask, b_red_mask)# 计算A组与B组红色区域重合的像素数量a_overlap_area = cv2.countNonZero(a_overlap)# 计算A组有颜色区域占B组红色区域的百分比overlap_percentage = (a_overlap_area / b_red_area) * 100 if b_red_area != 0 else 0return overlap_percentagedef process_images(a_folder, b_folder, output_file):# 获取文件夹中的所有文件a_files = sorted(os.listdir(a_folder))b_files = sorted(os.listdir(b_folder))# 打开输出文件with open(output_file, 'w') as f:# 遍历文件夹中的每一对图片for a_file, b_file in zip(a_files, b_files):# 拼接完整的文件路径a_image_path = os.path.join(a_folder, a_file)b_image_path = os.path.join(b_folder, b_file)# 确保文件是图片文件if not a_file.endswith(('.jpg', '.png', '.jpeg')) or not b_file.endswith(('.jpg', '.png', '.jpeg')):continue# 计算重叠百分比percentage = calculate_overlap_percentage(a_image_path, b_image_path)# 写入结果到txt文件f.write(f'{a_file} vs {b_file}: {percentage:.2f}%\n')print(f'{a_file} vs {b_file}: {percentage:.2f}%')# 文件夹路径
a_folder = 'path_to_a_folder' # A组文件夹路径
b_folder = 'path_to_b_folder' # B组文件夹路径
output_file = 'overlap_results.txt' # 输出的txt文件路径# 处理文件夹中的所有图片并输出到txt文件
process_images(a_folder, b_folder, output_file)
)