Source: Hi learning network sensitive and eager Forum www.piaodoo.com welcome to learn from each other
Examples of this paper is to share with you a specific code to find duplicate pictures and remove python, for your reference, as follows
And supporting the web crawler can also be used separately, too much repetition of images from the Internet to climb down, the identification code to support different sizes of the same picture, and delete the duplicate images, leaving only the first.
# -*- 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)
That's all for this article, I want to be helpful to learn, I hope you will support script home.
The original address is: http: //www.piaodoo.com/thread-13649-1-12.html Crazy Love www.eplbx.com 131 may help to better learning enjoyable than www.buzc.org learning! very good