1.查找重复图片

利用文件的MD5值可查找完全一样的重复图片

import os,time,hashlib

def getmd5(file):
    if not os.path.isfile(file):  
        return  
    fd = open(file,'rb')
    md5 = hashlib.md5()
    md5.update(fd.read())
    fd.close()
    return md5.hexdigest() 

if __name__ == "__main__":
    allfile = []
    md5list = []
    list_delete = []

    start = time.time()
    path = 'D:\\_PLAY\\新建文件夹\\'

    for filepath,dir,filelist in os.walk(path):
        for filename in filelist:
            allfile.append(os.path.join(filepath,filename))

    #根据MD5值比较
    for photo in allfile:
        md5sum = getmd5(photo)
        if md5sum not in md5list:
            md5list.append(md5sum)
        else:
            list_delete.append(photo)
    print('重复的照片有:',list_delete)
    
    #删除图片
    for i in range(len(list_delete)):
        os.remove(list_delete[i])
    

二.查找相似图片

本文采用四种哈希值进行比较：
1.感知哈希(perception hashing)
2.平均散列(average hashing)
3.梯度散列(difference hashing)
4.离散小波变换(wavelet hashing)

import os,imagehash
from PIL import Image

def hash(path):
    highfreq_factor = 4 # resize的尺度
    hash_size = 32 # 最终返回hash数值长度
    image_scale = 64
    img_size = hash_size * highfreq_factor
    list_file = []
    list_phash = []
    list_ahash = []
    list_dhash = []
    list_whash = []
    for file in os.listdir(path):
        if os.path.splitext(file)[1] == '.jpg':  
            path_file = os.path.join(path, file)  # 拼路径
            list_file.append(file)
            phash = imagehash.phash(Image.open(path_file),hash_size=hash_size,highfreq_factor=highfreq_factor)#感知哈希(perception hashing)
            ahash = imagehash.average_hash(Image.open(path_file),hash_size=hash_size)#平均散列(average hashing)
            dhash = imagehash.dhash(Image.open(path_file),hash_size=hash_size)#梯度散列(difference hashing)
            whash = imagehash.whash(Image.open(path_file),image_scale=image_scale,hash_size=hash_size,mode = 'db4')#离散小波变换(wavelet hashing)
            list_phash.append(phash)
            list_ahash.append(ahash)
            list_dhash.append(dhash)
            list_whash.append(whash)
    #print(list_hash)
    for i in range(len(list_file)):
        for j in range(i+1,len(list_file)):
            phash_value = 1-(list_phash[i]-list_phash[j])/len(list_phash[i].hash)**2
            ahash_value = 1-(list_ahash[i]-list_ahash[j])/len(list_ahash[i].hash)**2
            dhash_value = 1-(list_dhash[i]-list_dhash[j])/len(list_dhash[i].hash)**2
            whash_value = 1-(list_whash[i]-list_whash[j])/len(list_whash[i].hash)**2
            value_hash = max(phash_value,ahash_value,dhash_value,whash_value)
            if(value_hash > 0.9):#阈值设为0.9
                size_i = os.path.getsize(path + '\\' + list_file[i])
                size_j = os.path.getsize(path + '\\' + list_file[j])
                print(list_file[i],str(size_i/1024)+'KB')
                print(list_file[j],str(size_j/1024)+'KB')
                print(value_hash)
                print('***********************')

if __name__ == '__main__':
    path = r'D:\_PLAY\新建文件夹\Excel\ALL_Daily'
    hash(path)