将txt文件转为xml文件以适配图像标注工具labelimg或Pascal VOC XML 格式

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/Anymake_ren/article/details/80942069

labelimg作为图像领域目标检测、图像语义分割等领域常见的标注工具，输出的数据格式是Pascal VOC，实际工作中，我们经常需要把其他标注格式为txt的文件转为VOC的xml文件格式，下面的代码提供txt转VOC格式的xml文件的功能。

from xml.dom.minidom import Document
import os
import os.path
from PIL import Image

ann_path = "/Users/label_result.txt"
img_path = "/Users/"
xml_path = "/Users/"

if not os.path.exists(xml_path):
    os.mkdir(xml_path)

def writeXml(tmp, imgname,imgpath, w, h, label_list, wxml, attributes_list):
    doc = Document()
    #owner
    annotation = doc.createElement('annotation')
    doc.appendChild(annotation)
    #owner
    folder = doc.createElement('folder')
    annotation.appendChild(folder)
    folder_txt = doc.createTextNode("R_dataset")
    folder.appendChild(folder_txt)

    filename = doc.createElement('filename')
    annotation.appendChild(filename)
    filename_txt = doc.createTextNode(imgname)
    filename.appendChild(filename_txt)

    path = doc.createElement('path')
    annotation.appendChild(path)
    path_txt = doc.createTextNode(imgpath)
    path.appendChild(path_txt)
    #ones#
    source = doc.createElement('source')
    annotation.appendChild(source)

    database = doc.createElement('database')
    source.appendChild(database)
    database_txt = doc.createTextNode("The R Database")
    database.appendChild(database_txt)
    #onee#
    #twos#
    size = doc.createElement('size')
    annotation.appendChild(size)

    width = doc.createElement('width')
    size.appendChild(width)
    width_txt = doc.createTextNode(str(w))
    width.appendChild(width_txt)

    height = doc.createElement('height')
    size.appendChild(height)
    height_txt = doc.createTextNode(str(h))
    height.appendChild(height_txt)

    depth = doc.createElement('depth')
    size.appendChild(depth)
    depth_txt = doc.createTextNode("3")
    depth.appendChild(depth_txt)
    #twoe#
    segmented = doc.createElement('segmented')
    annotation.appendChild(segmented)
    segmented_txt = doc.createTextNode("0")
    segmented.appendChild(segmented_txt)

    # attributes
    attributes = doc.createElement("attributes")
    annotation.appendChild(attributes)

    for i in range(0,len(attributes_list)):
        #threes#
        attr_new = doc.createElement(attributes_list[i])
        attributes.appendChild(attr_new)
        attr_new_txt = doc.createTextNode(label_list[i])
        attr_new.appendChild(attr_new_txt)
        #threee#
    with open(wxml, "w") as f:
        f.write(doc.toprettyxml(indent = '\t', encoding='utf-8')) 
    f.close()

    # tempfile = tmp + "test.xml"
    # with open(tempfile, "w") as f:
    #     f.write(doc.toprettyxml(indent = '\t', encoding='utf-8'))

    # rewrite = open(tempfile, "r")
    # lines = rewrite.read().split('\n')
    # newlines = lines[1:len(lines)-1]

    # fw = open(wxml, "w")
    # for i in range(0, len(newlines)):
    #     fw.write(newlines[i] + '\n')

    # fw.close()
    # rewrite.close()
    # # os.remove(tempfile)
    return

attributes_list = [
    'Female',
    'AgeLess16',
    'Age17-30',
    'Age31-45',
    'BodyFat',
    'BodyNormal',
    'BodyThin'  
]

# temp = "/Users/data/temp"
# if not os.path.exists(temp):
#    os.mkdir(temp)

f = open(ann_path, 'r')
txt_list = f.readlines()
f.close()
im_name_list = []

for line in txt_list:
    line = line.strip()
    line_split = line.split(' ')
    img_name = line_split[0].split('/')[-1]
    im_name_list.append(img_name)
    label_list = []
    for j in range(1, len(line_split)):
        label_list.append(line_split[j])
    fileimgpath = os.path.join(img_path, img_name)
    im=Image.open(fileimgpath)  
    width= int(im.size[0])
    height= int(im.size[1])
    # print label_list
    savename = os.path.join(xml_path , img_name.split('.')[0] + '.xml')
    writeXml(temp, img_name,fileimgpath, width, height, label_list, savename,attributes_list)
# os.rmdir(temp)