前言
最近整理图片发现,好多图片都非常相似,于是写如下代码去删除,有两种方法:
注:第一种方法只对于连续图片(例一个视频里截下的图片)准确率也较高,其效率高;第二种方法准确率高,但效率低
方法一:相邻两个文件比较相似度,相似就把第二个加到新列表里,然后进行新列表去重,统一删除。
例如:有文件1-10,首先1和2相比较,若相似,则把2加入到新列表里,再接着2和3相比较,若不相似,则继续进行3和4比较…一直比到最后,然后删除新列表里的图片
代码如下:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import cv2
from skimage.measure import compare_ssim
# import shutil
# def yidong(filename1,filename2):
# shutil.move(filename1,filename2)
def delete(filename1):
os.remove(filename1)
if __name__ == '__main__':
path = r'D:\camera_pic\test\rec_pic'
# save_path_img = r'E:\0115_test\rec_pic'
# os.makedirs(save_path_img, exist_ok=True)
img_path = path
imgs_n = []
num = []
img_files = [os.path.join(rootdir, file) for rootdir, _, files in os.walk(path) for file in files if
(file.endswith('.jpg'))]
for currIndex, filename in enumerate(img_files):
if not os.path.exists(img_files[currIndex]):
print('not exist', img_files[currIndex])
break
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:
# yidong(image, save_path_img)
delete(image)
方法二:逐个去比较,若相似,则从原来列表删除,添加到新列表里,若不相似,则继续
例如:有文件1-10,首先1和2相比较,若相似,则把2在原列表删除同时加入到新列表里,再接着1和3相比较,若不相似,则继续进行1和4比较…一直比,到最后一个,再继续,正常应该再从2开始比较,但2被删除了,所以从3开始,继续之前的操作,最后把新列表里的删除。
代码如下:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import cv2
from skimage.measure import compare_ssim
import shutil
import datetime
def yidong(filename1,filename2):
shutil.move(filename1,filename2)
def delete(filename1):
os.remove(filename1)
print('real_time:',now_now-now)
if __name__ == '__main__':
path = r'F:\temp\demo'
# save_path_img = r'F:\temp\demo_save'
# os.makedirs(save_path_img, exist_ok=True)
for (root, dirs, files) in os.walk(path):
for dirc in dirs:
if dirc == 'rec_pic':
pic_path = os.path.join(root, dirc)
img_path = pic_path
imgs_n = []
num = []
del_list = []
img_files = [os.path.join(rootdir, file) for rootdir, _, files in os.walk(img_path) for file in files if
(file.endswith('.jpg'))]
for currIndex, filename in enumerate(img_files):
if not os.path.exists(img_files[currIndex]):
print('not exist', img_files[currIndex])
break
new_cur = 0
for i in range(10000000):
currIndex1 =new_cur
if currIndex1 >= len(img_files) - currIndex - 1:
break
else:
size = os.path.getsize(img_files[currIndex1 + currIndex + 1])
if size < 512:
# delete(img_files[currIndex + 1])
del_list.append(img_files.pop(currIndex1 + currIndex + 1))
else:
img = cv2.imread(img_files[currIndex])
img = cv2.resize(img, (46, 46), interpolation=cv2.INTER_CUBIC)
img1 = cv2.imread(img_files[currIndex1 + currIndex + 1])
img1 = cv2.resize(img1, (46, 46), interpolation=cv2.INTER_CUBIC)
ssim = compare_ssim(img, img1, multichannel=True)
if ssim > 0.9:
# imgs_n.append(img_files[currIndex + 1])
print(img_files[currIndex], img_files[currIndex1 + currIndex + 1], ssim)
del_list.append(img_files.pop(currIndex1 + currIndex + 1))
new_cur = currIndex1
else:
new_cur = currIndex1 + 1
print('small_ssim',img_files[currIndex], img_files[currIndex1 + currIndex + 1], ssim)
for image in del_list:
# yidong(image, save_path_img)
delete(image)
print('delete',image)
总结
到此这篇关于使用python如何删除同一文件夹下相似图片的文章就介绍到这了,更多相关python删除文件夹相似图片内容请搜索编程网以前的文章或继续浏览下面的相关文章希望大家以后多多支持编程网!