xml文件拆分 python_python 批量生成xml标记文件(连通域坐标分割)

#!/usr/bin/python#-*- coding=utf-8 -*-#author : Manuel#date: 2019-05-15

from xml.etree importElementTree as ETimportnumpy as npfrom skimage importdata,filters,segmentation,measure,morphology,colorfrom scipy.misc importimreadimportosfrom os importgetcwd

IMAGES_LIST=os.listdir('ls')#图片路径

#连通域分割,返回连通域坐标列表

defconnected_domain_position_get(image):

coordinates_list=[]#创建坐标列表

thresh = filters.threshold_otsu(image) #阈值分割，自动返回一个阈值

bw = morphology.closing(image >thresh,

morphology.square(3)) #(image > thresh, morphology.square(3)) #闭运算#将0，1转换成bool

cleared = bw.copy() #复制

segmentation.clear_border(cleared) #清除与边界相连的目标物

label_image = measure.label(cleared) #连通区域标记

borders = np.logical_xor(bw, cleared) #逻辑异或

label_image[borders] = -1 #?

#image_label_overlay = color.label2rgb(label_image, image=image) # 不同标记用不同颜色显示

for region in measure.regionprops(label_image): #循环得到每一个连通区域属性集

#忽略小区域

if region.area < 1000:continue

#print(region.bbox)

#绘制外包矩形

minr, minc, maxr, maxc =region.bbox#rect = mpatches.Rectangle((minc - 10, minr - 10), maxc - minc + 20, maxr - minr + 20,

#fill=False, edgecolor='red',

#linewidth=2) # mpatches.Rectangle(矩形左上顶点坐标(x，y), width, height)

left = minc - 10upper= minr - 10right= maxc + 10lower= maxr + 10coordinates_list.append([left,upper,right,lower])#将每组连通域坐标添加进坐标列表

return coordinates_list#返回连通域坐标列表

#创建一级分支object

def create_object(root,xi,yi,xa,ya):#参数依次，树根，xmin，ymin，xmax，ymax

#创建一级分支object

_object=ET.SubElement(root,'object')#创建二级分支

name=ET.SubElement(_object,'name')

name.text='AreaMissing'pose=ET.SubElement(_object,'pose')

pose.text='Unspecified'truncated=ET.SubElement(_object,'truncated')

truncated.text='0'difficult=ET.SubElement(_object,'difficult')

difficult.text='0'

#创建bndbox

bndbox=ET.SubElement(_object,'bndbox')

xmin=ET.SubElement(bndbox,'xmin')

xmin.text='%s'%xi

ymin= ET.SubElement(bndbox, 'ymin')

ymin.text= '%s'%yi

xmax= ET.SubElement(bndbox, 'xmax')

xmax.text= '%s'%xa

ymax= ET.SubElement(bndbox, 'ymax')

ymax.text= '%s'%ya#创建xml文件

defcreate_tree(image_name):globalannotation#创建树根annotation

annotation = ET.Element('annotation')#创建一级分支folder

folder = ET.SubElement(annotation,'folder')#添加folder标签内容

folder.text=('ls')#创建一级分支filename

filename=ET.SubElement(annotation,'filename')

filename.text=image_name.strip('.jpg')#创建一级分支path

path=ET.SubElement(annotation,'path')

path.text=getcwd()+'/ls/%s'%image_name#用于返回当前工作目录

#创建一级分支source

source=ET.SubElement(annotation,'source')#创建source下的二级分支database

database=ET.SubElement(source,'database')

database.text='Unknown'

#创建一级分支size

size=ET.SubElement(annotation,'size')#创建size下的二级分支图像的宽、高及depth

width=ET.SubElement(size,'width')

width.text='512'height=ET.SubElement(size,'height')

height.text='384'depth= ET.SubElement(size,'depth')

depth.text= '3'

#创建一级分支segmented

segmented = ET.SubElement(annotation,'segmented')

segmented.text= '0'

defmain():for image_name inIMAGES_LIST:#只处理jpg文件

if image_name.endswith('jpg'):#将图像通过连通域分割，得到连通域坐标列表，该列表的形式[[a,b,c,d],[e,f,g,h]...,]

image = color.rgb2gray(imread(os.path.join(r'./ls', image_name)))

coordinates_list=connected_domain_position_get(image)

create_tree(image_name)for coordinate_list incoordinates_list:

create_object(annotation, coordinate_list[0], coordinate_list[1], coordinate_list[2], coordinate_list[3])#if coordinates_list==[]:

#break

#将树模型写入xml文件

tree =ET.ElementTree(annotation)

tree.write('ls/%s.xml' % image_name.strip('.jpg'))if __name__ == '__main__':

main()