关于图像指纹的一些想法

import cv2
import numpy as np
import os
import time
#灰度直方图
def classify_gray_hist(image1, image2, size=(256, 256)):
    # 先调整大小
    image1 = cv2.resize(image1, size)
    image2 = cv2.resize(image2, size)
    hist1 = cv2.calcHist([image1], [0], None, [256], [0.0, 255.0])
    hist2 = cv2.calcHist([image2], [0], None, [256], [0.0, 255.0])
    # 计算直方图的重合度
    degree = 0
    for i in range(len(hist1)):
        if hist1[i] != hist2[i]:
            degree = degree + (1 - (abs(hist1[i] - hist2[i]) / max(hist1[i], hist2[i])))
        else:
            degree = degree + 1
    degree = degree / len(hist1)
    return degree


def classify_hist_with_split(image1, image2, size=(256, 256)):
    # 将图像resize后，分类为三个通道，再计算每个通道的相似值
    image1 = cv2.resize(image1, size)
    image2 = cv2.resize(image2, size)
    sub_image1 = cv2.split(image1)
    sub_image2 = cv2.split(image2)
    sub_data = 0
    for im1, im2 in zip(sub_image1, sub_image2):
        sub_data += calculate(im1, im2)
    sub_data = sub_data / 3
    return sub_data


def calculate(im1, im2):
    hist1 = cv2.calcHist([im1], [0], None, [256], [0.0, 255.0])
    hist2 = cv2.calcHist([im2], [0], None, [256], [0.0, 255.0])
    degree = 0
    for i in range(len(hist1)):
        if hist1[i] != hist2[i]:
            degree = degree + (1 - (abs(hist1[i] - hist2[i]) / max(hist1[i], hist2[i])))
        else:
            degree = degree + 1
    degree = degree / len(hist1)
    return degree


# 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)  # 切换至灰度图
    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)  # 切换至灰度图
    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]
    #print(dct1)
    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)  # 计算像素平均值
    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 = 0
    for index in range(len(hash1)):
        if hash1[index] != hash2[index]:
            num += 1
    return num


# 差异值哈希算法
def dhash(image1, image2):
    image1 = cv2.resize(image1, (9, 8))
    image2 = cv2.resize(image2, (9, 8))
    gray1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)  # 切换至灰度图
    gray2 = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)
    hash1 = dhashcaulate(gray1)
    hash2 = dhashcaulate(gray2)
    return Hamming_distance(hash1, hash2)


def dhashcaulate(gray):
    hash_str = ''
    for i in range(8):
        for j in range(8):
            if gray[i, j] > gray[i, j + 1]:
                hash_str = hash_str + '1'
            else:
                hash_str = hash_str + '0'
    return hash_str


if __name__ == '__main__':
    base_path = './base'
    repeat_path = './repeat'
    unrepeat_path = './unrepeat'
    A = 0
    cnt = 0
    B = 0
    T = time.time()
    for unrepeat in os.listdir(unrepeat_path):
        imgobj1 = cv2.imread('./unrepeat/' + unrepeat)
        for base in os.listdir(base_path):
            imgobj2 = cv2.imread('./base/' + base)
            cnt = cnt + 1
            #degree = classify_gray_hist(imgobj1,imgobj2)   #单通道直方图
            #degree = classify_hist_with_split(imgobj1,imgobj2)  #三通道直方图
            #degree = classify_aHash(imgobj1,imgobj2)          #平均哈希法
            #degree = classify_pHash(imgobj1,imgobj2)          #感知哈希法
            degree = dhash(imgobj1, imgobj2)  # 差异值哈希算法
            if degree < 5:
                A = A + 1
                break

    for repeat in os.listdir(repeat_path):
        imgobj1 = cv2.imread('./repeat/' + repeat)
        for base in os.listdir(base_path):
            imgobj2 = cv2.imread('./base/' + base)
            cnt = cnt + 1
            #degree = classify_gray_hist(imgobj1,imgobj2)   #单通道直方图
            #degree = classify_hist_with_split(imgobj1,imgobj2)  #三通道直方图
            #degree = classify_aHash(imgobj1,imgobj2)          #平均哈希法
            #degree = classify_pHash(imgobj1,imgobj2)          #感知哈希法
            degree = dhash(imgobj1, imgobj2)  # 差异值哈希算法
            if degree < 5 :
                #print (degree)
                B = B + 1
                break
    FT = time.time();
    print("unrepeat: " + str(A) +", repeat:"+  str(B) + ", time: " + str(FT - T)+", avg_time:" + str((FT-T)/cnt) )