Python通过XML标注文件用框把标注物体找出

目录

• 实现1
• 实现2

实现1

from __future__ import division
import os
from PIL import Image
import xml.dom.minidom
import numpy as np
ImgPath = r'E:/正课/大二上/计算机网络/网络编程/Taidi/train/train'
AnnoPath = r'E:/正课/大二上/计算机网络/网络编程/Taidi/train/train'
ProcessedPath = r'E:/正课/大二上/计算机网络/网络编程/Taidi/train'

imagelist = os.listdir(ImgPath)

for image in imagelist:
    image_pre, ext = os.path.splitext(image)
    imgfile = ImgPath + image
    # print(imgfile)
    if not os.path.exists(AnnoPath + image_pre + '.xml' ):
        continue
    xmlfile = AnnoPath + image_pre + '.xml'
    DomTree = xml.dom.minidom.parse(xmlfile)
    annotation = DomTree.documentElement
    filenamelist = annotation.getElementsByTagName('filename')
    filename = filenamelist[0].childNodes[0].data
    objectlist = annotation.getElementsByTagName('object')
    i = 1
    for objects in objectlist:
        namelist = objects.getElementsByTagName('name')
        objectname = namelist[0].childNodes[0].data
        savepath = ProcessedPath + objectname
        if not os.path.exists(savepath):
            os.makedirs(savepath)
        bndbox = objects.getElementsByTagName('bndbox')
        cropboxes = []
        for box in bndbox:
            x1_list = box.getElementsByTagName('xmin')
            x1 = int(x1_list[0].childNodes[0].data)
            y1_list = box.getElementsByTagName('ymin')
            y1 = int(y1_list[0].childNodes[0].data)
            x2_list = box.getElementsByTagName('xmax')
            x2 = int(x2_list[0].childNodes[0].data)
            y2_list = box.getElementsByTagName('ymax')
            y2 = int(y2_list[0].childNodes[0].data)
            w = x2 - x1
            h = y2 - y1
            obj = np.array([x1,y1,x2,y2])
            shift = np.array([[1,1,1,1]])
            XYmatrix = np.tile(obj,(1,1))
            cropboxes = XYmatrix * shift
            img = Image.open(imgfile)
            for cropbox in cropboxes:
                cropedimg = img.crop(cropbox)
                cropedimg.save(savepath + '/' + image_pre + '_' + str(i) + '.jpg')
                print(savepath + '/' + image_pre + '_' + str(i) + '.jpg')
                i += 1

实现2

import os
import xml.dom.minidom
import cv2 as cv

ImgPath = r"C:\Users\WalterJ726\Desktop\train\train"
AnnoPath = r"C:\Users\WalterJ726\Desktop\train\train" # xml文件地址
save_path = r"C:\Users\WalterJ726\Desktop\train"

def draw_anchor(ImgPath, AnnoPath, save_path):
    imagelist = os.listdir(ImgPath)
    for image in imagelist:
        image_pre, ext = os.path.splitext(image)
        imgfile = ImgPath + image
        xmlfile = AnnoPath + image_pre + '.xml'
        #print(image)
        # 打开xml文档
        DOMTree = xml.dom.minidom.parse(xmlfile)
        # 得到文档元素对象
        collection = DOMTree.documentElement
        # 读取图片
        img = cv.imread(imgfile)

        filenamelist = collection.getElementsByTagName("filename")
        filename = filenamelist[0].childNodes[0].data
        #print(filename)
        # 得到标签名为object的信息
        objectlist = collection.getElementsByTagName("object")

        for objects in objectlist:
            # 每个object中得到子标签名为name的信息
            namelist = objects.getElementsByTagName('name')
            # 通过此语句得到具体的某个name的值
            objectname = namelist[0].childNodes[0].data
            print(objectname)

            bndbox = objects.getElementsByTagName('bndbox')
            # print(bndbox)
            for box in bndbox:
                x1_list = box.getElementsByTagName('xmin')
                x1 = int(x1_list[0].childNodes[0].data)
                y1_list = box.getElementsByTagName('ymin')
                y1 = int(y1_list[0].childNodes[0].data)
                x2_list = box.getElementsByTagName('xmax')  # 注意坐标，看是否需要转换
                x2 = int(x2_list[0].childNodes[0].data)
                y2_list = box.getElementsByTagName('ymax')
                y2 = int(y2_list[0].childNodes[0].data)
                cv.rectangle(img, (x1, y1), (x2, y2), (255, 255, 255), thickness=2)
                cv.putText(img, objectname, (x1, y1), cv.FONT_HERSHEY_COMPLEX, 0.7, (0, 255, 0),
                           thickness=2)
                # cv.imshow('head', img)
                cv.imwrite(save_path + '/' + filename, img)  # save picture
draw_anchor(ImgPath, AnnoPath, save_path)