python查找重復(fù)圖片并刪除（圖片去重）-創(chuàng)新互聯(lián)

本文實例為大家分享了python查找重復(fù)圖片并刪除的具體代碼，供大家參考，具體內(nèi)容如下

網(wǎng)站的建設(shè)成都創(chuàng)新互聯(lián)公司專注網(wǎng)站定制,經(jīng)驗豐富,不做模板,主營網(wǎng)站定制開發(fā).小程序定制開發(fā),H5頁面制作!給你煥然一新的設(shè)計體驗!已為水泥攪拌車等企業(yè)提供專業(yè)服務(wù)。

和網(wǎng)絡(luò)爬蟲配套的，也可單獨使用，從網(wǎng)上爬下來的圖片重復(fù)太多，代碼支持識別不同尺寸大小一致的圖片，并把重復(fù)的圖片刪除，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)

當(dāng)前標(biāo)題：python查找重復(fù)圖片并刪除（圖片去重）-創(chuàng)新互聯(lián)
網(wǎng)站URL：http://muchs.cn/article12/ejgdc.html

成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián)，為您提供云服務(wù)器、靜態(tài)網(wǎng)站、商城網(wǎng)站、手機網(wǎng)站建設(shè)、微信公眾號、網(wǎng)站收錄

廣告

聲明：本網(wǎng)站發(fā)布的內(nèi)容（圖片、視頻和文字）以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主，如果涉及侵權(quán)請盡快告知，我們將會在第一時間刪除。文章觀點不代表本網(wǎng)站立場，如需處理請聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載，或轉(zhuǎn)載時需注明來源： 創(chuàng)新互聯(lián)