Python–图片去重 按文件大小读取
最近在做图片处理任务
分完图片发现有很多一样的
但是python os.walk()返回的的文件列表顺序会不一样
之前写的代码 要全部遍历所有图片 一张图和剩下所有图对比 虽然说准确率很高 但是效率特别低
然后我发现在文件夹里把图片按大小排序相似的图片会相邻
这样只要相邻图片对比就能move (意思是1和2对比,3和4对比等等)不用全部遍历就可了 虽然不能做到100%准确 但是速度大大提升!我快乐了!之前遍历全部的六千张图我跑了一天……
附代码
import os
import cv2
from skimage.measure import compare_ssim
import shutil
import random
def delete(filename1):
os.remove(filename1)
def move(filename1,filename2):
shutil.move(filename1,filename2)
if __name__ == '__main__':
path = r'C:\Users\lenovo\Desktop\image_all\0'
save_path_img = r'C:\Users\lenovo\Desktop\image_all\delete1'
os.makedirs(save_path_img, exist_ok=True)
fileMap = {}
size = 0
# 遍历filePath下的文件、文件夹(包括子目录)
for parent, dirnames, filenames in os.walk(path):
#for dirname in dirnames:
# print('parent is %s, dirname is %s' % (parent, dirname))
for filename in filenames:
# print('parent is %s, filename is %s' % (parent, filename))
# print('the full name of the file is %s' % os.path.join(parent, filename))
size = os.path.getsize(os.path.join(parent, filename))
fileMap.setdefault(os.path.join(parent, filename), size)
filelist = sorted(fileMap.items(), key=lambda d: d[1], reverse=False)
img_files= []
for filename, size in filelist:
img_files.append(filename)
# print("filename is %s , and size is %d" % (filename, size))
imgs_n = []
num = []
print(img_files)
for currIndex, filename in enumerate(img_files):
img = cv2.imread(img_files[currIndex])
img1 = cv2.imread(img_files[currIndex + 1])
ssim = compare_ssim(img, img1, multichannel=True)
if ssim > 0.9:
imgs_n.append(img_files[currIndex + 1])
print(img_files[currIndex], img_files[currIndex + 1], ssim)
else:
print('small_ssim',img_files[currIndex], img_files[currIndex + 1], ssim)
currIndex += 1
if currIndex >= len(img_files)-1:
break
for image in imgs_n:
move(image, save_path_img)
# delete(image)
代码部分有所参考一些博文 但是不知道哪里看得了 请见谅 作者看到可私信我 我附上引用链接啦
嘻嘻 这是我入驻CSDN的第一篇文章哎
本文链接:https://blog.csdn.net/weixin_42385606/article/details/104718533