使用python opencv對目錄下圖片進行去重

版本：

平臺：ubuntu 14 / I5 / 4G內存

python版本：python2.7

opencv版本：2.13.4

依賴：

如果系統沒有python，則需要進行安裝

sudo apt-get install python

sudo apt-get install python-dev

sudo apt-get install python-pip

sudo pip install numpy mathplotlib 

sudo apt-get install libcv-dev

sudo apt-get install python-opencv

使用感知哈希算法進行圖片去重

原理：對每個文件進行遍歷所有進行去重，因此圖片越多速度越慢，但是可以節省手動操作

感知哈希原理：

1、需要比較的圖片都縮放成8*8大小的灰度圖

2、獲得每個圖片每個像素與平均值的比較，得到指紋

3、根據指紋計算漢明距離

5、如果得出的不同的元素小於5則爲相同（相似？）的圖片

#!/usr/bin/python
# -*- 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
     
def main(argv):
    if len(argv) <= 1:
        print "command error"
        return -1
    if os.path.exists(argv[1]) is False:
        return -1
    path = argv[1]
    '''
    while True:
        if cmpandremove(path) == 0:
            break
    '''
    cmpandremove(path)
    return 0
            
if __name__ == '__main__':
    main(sys.argv)

爲了節省操作，遍歷所有目錄，把想要去重的目錄遍歷一遍

#!/bin/bash
indir=$1
addcount=0
function intest()
{
    
    for file in $1/*
    do
        echo $file
        if test -d $file 
        then
            ~/similar.py $file/
            intest $file
        fi
    done
}

intest $indir