医疗资料ROI mask转YOLO的bounding box

Question

我要怎么写出一个自动化的class或def来“自动画出” ， “YOLOv5”或其他YOLO格式的bounding box？
并且生出.txt文件？
想要框住的图像如下ROI范例：

Answer 1

该回答引用ChatGPT
请参考下面的解决方案，如果有帮助，还请点击 “采纳” 感谢支持！

下面是使用Python和OpenCV库的示例代码

import cv2

def draw_bounding_box(img, object_list):
    for obj in object_list:
        xmin, ymin, xmax, ymax = obj['coordinates']
        cv2.rectangle(img, (xmin, ymin), (xmax, ymax), (0, 0, 255), 2)
    return img

def detect_objects(img):
    # Add your object detection code here
    # ...
    object_list = [{'coordinates': (100, 100, 200, 200)}]
    return object_list

def save_to_txt(object_list, file_name):
    with open(file_name, 'w') as f:
        for obj in object_list:
            xmin, ymin, xmax, ymax = obj['coordinates']
            line = ' '.join([str(xmin), str(ymin), str(xmax), str(ymax)])
            f.write(line + '\n')

def main(img_file, txt_file):
    img = cv2.imread(img_file)
    object_list = detect_objects(img)
    img = draw_bounding_box(img, object_list)
    save_to_txt(object_list, txt_file)
    cv2.imwrite('output.jpg', img)

if __name__ == '__main__':
    main('input.jpg', 'output.txt')