python查找重复图片并删除（图片去重）-创新互联

本文实例为大家分享了python查找重复图片并删除的具体代码，供大家参考，具体内容如下

和网络爬虫配套的，也可单独使用，从网上爬下来的图片重复太多，代码支持识别不同尺寸大小一致的图片，并把重复的图片删除，只保留第一份。

# -*- coding: utf-8 -*-
import cv2
import numpy as np
import os,sys,types

def cmpandremove2(path):
  dirs = os.listdir(path)
  dirs.sort()
  if len(dirs) <= 0:
    return
  dict={}
  for i in dirs:
    prepath = path + "/" + i
    preimg = cv2.imread(prepath)
    if type(preimg) is types.NoneType:
      continue
    preresize = cv2.resize(preimg, (8,8))
    pregray = cv2.cvtColor(preresize, cv2.COLOR_BGR2GRAY)
    premean = cv2.mean(pregray)[0]
    prearr = np.array(pregray.data)
    for j in range(0,len(prearr)):
      if prearr[j] >= premean:
        prearr[j] = 1
      else:
        prearr[j] = 0
    print "get", prepath
    dict[i] = prearr
  dictkeys = dict.keys()
  dictkeys.sort()
  index = 0
  while True:
    if index >= len(dictkeys):
      break
    curkey = dictkeys[index]
    dellist=[]
    print curkey
    index2 = index
    while True:
      if index2 >= len(dictkeys):
        break
      j = dictkeys[index2]
      if curkey == j:
        index2 = index2 + 1
        continue
      arr1 = dict[curkey]
      arr2 = dict[j]
      diff = 0
      for k in range(0,len(arr2)):
        if arr1[k] != arr2[k]:
          diff = diff + 1
      if diff <= 5:
        dellist.append(j)
      index2 = index2 + 1
    if len(dellist) > 0:
      for j in dellist:
        file = path + "/" + j
        print "remove", file
        os.remove(file)
        dict.pop(j)
      dictkeys = dict.keys()
      dictkeys.sort()
    index = index + 1


def cmpandremove(path):
  index = 0
  flag = 0
  dirs = os.listdir(path)
  dirs.sort()
  if len(dirs) <= 0:
    return 0
  while True:
    if index >= len(dirs):
      break
    prepath = path + dirs[index]
    print prepath
    index2 = 0
    preimg = cv2.imread(prepath)
    if type(preimg) is types.NoneType:
      index = index + 1
      continue
    preresize = cv2.resize(preimg, (8, 8))
    pregray = cv2.cvtColor(preresize, cv2.COLOR_BGR2GRAY)
    premean = cv2.mean(pregray)[0]
    prearr = np.array(pregray.data)
    for i in range(0, len(prearr)):
      if prearr[i] >= premean:
        prearr[i] = 1
      else:
        prearr[i] = 0
    removepath = []
    while True:
      if index2 >= len(dirs):
        break
      if index2 != index:
        curpath = path + dirs[index2]
        # print curpath
        curimg = cv2.imread(curpath)
        if type(curimg) is types.NoneType:
          index2 = index2 + 1
          continue
        curresize = cv2.resize(curimg, (8, 8))
        curgray = cv2.cvtColor(curresize, cv2.COLOR_BGR2GRAY)
        curmean = cv2.mean(curgray)[0]
        curarr = np.array(curgray.data)
        for i in range(0, len(curarr)):
          if curarr[i] >= curmean:
            curarr[i] = 1
          else:
            curarr[i] = 0
        diff = 0
        for i in range(0, len(curarr)):
          if curarr[i] != prearr[i]:
            diff = diff + 1
        if diff <= 5:
          print 'the same'
          removepath.append(curpath)
          flag = 1
      index2 = index2 + 1
    index = index + 1
    if len(removepath) > 0:
      for file in removepath:
        print "remove", file
        os.remove(file)
      dirs = os.listdir(path)
      dirs.sort()
      if len(dirs) <= 0:
        return 0
        # index = 0
  return flag


path = 'pics/'
cmpandremove(path)