import 

import csv
import glob
import os
import cv2
import numpy as np
try:from scipy.misc import imread
except ImportError:from imageio import imreadroot_dir_1 = "C:/Users/chenxu/Desktop/image"   #目录1：无标签数据
root_dir_2 = "C:/Users/chenxu/Desktop/ori_match/"  #目录2：有标签数据
suffix = ".png"
target_lst = []
token2target = {}
data = []# 平均哈希算法计算
def classify_aHash(image1,image2):image1 = cv2.resize(image1, (8, 8))image2 = cv2.resize(image2, (8, 8))gray1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)gray2 = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)hash1 = getHash(gray1)hash2 = getHash(gray2)return Hamming_distance(hash1, hash2)def classify_pHash(image1,image2):image1 = cv2.resize(image1, (32, 32))image2 = cv2.resize(image2, (32, 32))gray1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)gray2 = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)# 将灰度图转为浮点型，再进行dct变换dct1 = cv2.dct(np.float32(gray1))dct2 = cv2.dct(np.float32(gray2))# 取左上角的8*8，这些代表图片的最低频率# 这个操作等价于c++中利用opencv实现的掩码操作# 在python中进行掩码操作，可以直接这样取出图像矩阵的某一部分dct1_roi = dct1[0:8, 0:8]dct2_roi = dct2[0:8, 0:8]hash1 = getHash(dct1_roi)hash2 = getHash(dct2_roi)return Hamming_distance(hash1, hash2)# 输入灰度图，返回hash
def getHash(image):avreage = np.mean(image)hash = []for i in range(image.shape[0]):for j in range(image.shape[1]):if image[i, j] > avreage:hash.append(1)else:hash.append(0)return hash# 计算汉明距离
def Hamming_distance(hash1,hash2):num = 0for index in range(len(hash1)):if hash1[index] != hash2[index]:num += 1return numif __name__ == "__main__":file_lst = os.listdir(root_dir_1)image_nums = len(file_lst)   #未标记图片总数for img_num in range(image_nums):addr1 = root_dir_1 + '/' + "image_" + str(img_num) + suffiximg_1 = cv2.imread(addr1)label = 0       #找到相应类别标记位target_lst = []  #存储对应7种分类对应数字名for dir_name in glob.glob(os.path.join(root_dir_2, "*")):target = os.path.split(dir_name)[-1]   #依次取每个类别下图片与未分类图片进行比较if target not in target_lst:            #若相似度很高，则将未分类图片标记为此分类图片对应的类别target_lst.append(target)token2target[len(target_lst)-1] = targetfor img_name in glob.glob(os.path.join(dir_name, "*" + suffix)):img_2 = cv2.imread(img_name)degree = classify_aHash(img_1, img_2)  #degree越小，相似度越高num = len(target_lst) - 1if degree < 3:           #degree=0,1,2，若限制degree=0，会有很多图片无法匹配到相应类别d1 = tuple(str(num))data.append(d1)label = 1breakif label == 1:breakif label == 0:d2 = tuple("N")  #如果没发现相应的分类，则标记为Ndata.append(d2)print(data)print(token2target)print(data)#将生成data导出为CSVwith open("./pic_match.csv", "w", newline="", encoding='utf-8-sig') as datacsv:csvwriter = csv.writer(datacsv, dialect=("excel"))csvwriter.writerows(data)