图像预处理：另存xml文件坐标中bndbox的局部图片

飞奔đ小蜗牛

于 2023-03-04 08:56:52 发布

阅读量99

点赞数

分类专栏：学习笔记图像处理文章标签： xml python opencv

本文链接：https://blog.csdn.net/zhao602Q/article/details/129330189

版权

学习笔记同时被 2 个专栏收录

13 篇文章 0 订阅

订阅专栏

图像处理

1 篇文章 0 订阅

订阅专栏

# -*- coding: utf-8 -*-
# @Time  : 2020/2/8 22:14
# @Author : SanZhi
# @File  : get_xml.py
# @Software: PyCharm
import cv2
import xml.dom.minidom
import os
def main():
  # JPG文件的地址
  img_path = 'C:/Faster-RCNN-TensorFlow-Python3-master/data/VOCdevkit2007/VOC2007/JPEGImages/'
  # XML文件的地址
  anno_path = 'C:/Faster-RCNN-TensorFlow-Python3-master/data/VOCdevkit2007/VOC2007/Annotations/'
  # 存结果的文件夹
  cut_path = 'C:/Faster-RCNN-TensorFlow-Python3-master/data/demo_roi_cut/'
  # 获取文件夹中的文件
  imagelist = os.listdir(img_path)

  for image in imagelist:
    image_pre, ext = os.path.splitext(image)
    img_file = img_path + image
    img = cv2.imread(img_file)
    xml_file = anno_path + image_pre + '.xml'
    DOMTree = xml.dom.minidom.parse(xml_file)
    collection = DOMTree.documentElement
    objects = collection.getElementsByTagName("object")

    for object in objects:
      print("start")
      bndbox = object.getElementsByTagName('bndbox')[0]
      xmin = bndbox.getElementsByTagName('xmin')[0]
      xmin_data = xmin.childNodes[0].data
      ymin = bndbox.getElementsByTagName('ymin')[0]
      ymin_data = ymin.childNodes[0].data
      xmax = bndbox.getElementsByTagName('xmax')[0]
      xmax_data = xmax.childNodes[0].data
      ymax = bndbox.getElementsByTagName('ymax')[0]
      ymax_data = ymax.childNodes[0].data
      xmin = int(xmin_data)
      xmax = int(xmax_data)
      ymin = int(ymin_data)
      ymax = int(ymax_data)
      img_cut = img[ymin:ymax, xmin:xmax, :]
      cv2.imwrite(cut_path + 'cut_img_{}.jpg'.format(image_pre), img_cut)


if __name__ == '__main__':
  main()