实现LabelImg标注的xml文件和文件夹下的图片匹配，删除漏标注的图像_在labelimg中未标注的图片将其删除的程序

# coding: utf-8
from PIL import Image
import os
import os.path
import numpy as np
import cv2
import glob
import pandas as pd
import xml.etree.ElementTree as ET
import time

start = time.time()

# 指明被遍历的文件夹
rootdir = r'E:/picture/water/waterDatasets/renameWater'
for parent, dirnames, filenames in os.walk(rootdir):  # 遍历每一张图片
    for filename in filenames:
        # print('parent is :' + parent)
        # print('filename is :' + filename)
        currentPath = os.path.join(parent, filename)
        print('the fulll name of the file is :' + currentPath)

        img = Image.open(currentPath)
        #  print (img.format, img.size, img.mode)
        # img.show()

        path = r'E:/picture/water/waterDatasets/annotations/'
        for xml_file in glob.glob(path + '/*.xml'):
            # 返回解析树
            tree = ET.parse(xml_file)
            # 获取根节点
            root = tree.getroot()
            # print(root)
            # 根据标签名查找root下的所有标签，并获取其值
            # print(imgname)
            # 对所有目标进行解析
            for member in root.findall('object'):
                xmlname = root.find('filename').text
                #savefilename = member.find('name').text

                if xmlname == filename:
                    pic_file_path = os.path.join(path, xmlname)
                    os.remove(pic_file_path)

end = time.time()
print("Execution Time:", end - start)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46