phpcms网站转移/网络推广经验

# -*- coding: utf-8 -*-
# !/usr/bin/env python
# 余弦相似度计算
from PIL import Image
from numpy import average, dot, linalg
# 对图片进行统一化处理
def get_thum(image, size=(64, 64), greyscale=False):# 利用image对图像大小重新设置, Image.ANTIALIAS为高质量的image = image.resize(size, Image.ANTIALIAS)if greyscale:# 将图片转换为L模式，其为灰度图，其每个像素用8个bit表示image = image.convert('L')return image
# 计算图片的余弦距离
def image_similarity_vectors_via_numpy(image1, image2):image1 = get_thum(image1)image2 = get_thum(image2)images = [image1, image2]vectors = []norms = []for image in images:vector = []for pixel_tuple in image.getdata():vector.append(average(pixel_tuple))vectors.append(vector)# linalg=linear（线性）+algebra（代数），norm则表示范数# 求图片的范数norms.append(linalg.norm(vector, 2))a, b = vectorsa_norm, b_norm = norms# dot返回的是点积，对二维数组（矩阵）进行计算res = dot(a / a_norm, b / b_norm)return res
image1 = Image.open('010.jpg')
image2 = Image.open('011.jpg')
cosin = image_similarity_vectors_via_numpy(image1, image2)
print('图片余弦相似度', cosin)

import cv2
import numpy as np
from PIL import Image
import requests
from io import BytesIO
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as pltdef aHash(img):# 均值哈希算法# 缩放为8*8img = cv2.resize(img, (8, 8))# 转换为灰度图gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# s为像素和初值为0，hash_str为hash值初值为''s = 0hash_str = ''# 遍历累加求像素和for i in range(8):for j in range(8):s = s+gray[i, j]# 求平均灰度avg = s/64# 灰度大于平均值为1相反为0生成图片的hash值for i in range(8):for j in range(8):if gray[i, j] > avg:hash_str = hash_str+'1'else:hash_str = hash_str+'0'return hash_strdef dHash(img):# 差值哈希算法# 缩放8*8img = cv2.resize(img, (9, 8))# 转换灰度图gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)hash_str = ''# 每行前一个像素大于后一个像素为1，相反为0，生成哈希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_strdef pHash(img):# 感知哈希算法# 缩放32*32img = cv2.resize(img, (32, 32))   # , interpolation=cv2.INTER_CUBIC# 转换为灰度图gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# 将灰度图转为浮点型，再进行dct变换dct = cv2.dct(np.float32(gray))# opencv实现的掩码操作dct_roi = dct[0:8, 0:8]hash = []avreage = np.mean(dct_roi)for i in range(dct_roi.shape[0]):for j in range(dct_roi.shape[1]):if dct_roi[i, j] > avreage:hash.append(1)else:hash.append(0)return hashdef calculate(image1, image2):# 灰度直方图算法# 计算单通道的直方图的相似值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 = 0for 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 + 1degree = degree / len(hist1)return degreedef classify_hist_with_split(image1, image2, size=(256, 256)):# RGB每个通道的直方图相似度# 将图像resize后，分离为RGB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 = 0for im1, im2 in zip(sub_image1, sub_image2):sub_data += calculate(im1, im2)sub_data = sub_data / 3return sub_datadef cmpHash(hash1, hash2):# Hash值对比# 算法中1和0顺序组合起来的即是图片的指纹hash。顺序不固定，但是比较的时候必须是相同的顺序。# 对比两幅图的指纹，计算汉明距离，即两个64位的hash值有多少是不一样的，不同的位数越小，图片越相似# 汉明距离：一组二进制数据变成另一组数据所需要的步骤，可以衡量两图的差异，汉明距离越小，则相似度越高。汉明距离为0，即两张图片完全一样n = 0# hash长度不同则返回-1代表传参出错if len(hash1) != len(hash2):return -1# 遍历判断for i in range(len(hash1)):# 不相等则n计数+1，n最终为相似度if hash1[i] != hash2[i]:n = n + 1return ndef getImageByUrl(url):# 根据图片url 获取图片对象html = requests.get(url, verify=False)image = Image.open(BytesIO(html.content))return imagedef PILImageToCV():# PIL Image转换成OpenCV格式path = "/Users/waldenz/Documents/Work/doc/TestImages/t3.png"img = Image.open(path)plt.subplot(121)plt.imshow(img)print(isinstance(img, np.ndarray))img = cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)print(isinstance(img, np.ndarray))plt.subplot(122)plt.imshow(img)plt.show()def CVImageToPIL():# OpenCV图片转换为PIL imagepath = "/Users/waldenz/Documents/Work/doc/TestImages/t3.png"img = cv2.imread(path)# cv2.imshow("OpenCV",img)plt.subplot(121)plt.imshow(img)img2 = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))plt.subplot(122)plt.imshow(img2)plt.show()def bytes_to_cvimage(filebytes):# 图片字节流转换为cv imageimage = Image.open(filebytes)img = cv2.cvtColor(np.asarray(image), cv2.COLOR_RGB2BGR)return imgdef runAllImageSimilaryFun(para1, para2):# 均值、差值、感知哈希算法三种算法值越小，则越相似,相同图片值为0# 三直方图算法和单通道的直方图 0-1之间，值越大，越相似。 相同图片为1# t1,t2   14;19;10;  0.70;0.75# t1,t3   39 33 18   0.58 0.49# s1,s2  7 23 11     0.83 0.86  挺相似的图片# c1,c2  11 29 17    0.30 0.31if para1.startswith("http"):# 根据链接下载图片，并转换为opencv格式img1 = getImageByUrl(para1)img1 = cv2.cvtColor(np.asarray(img1), cv2.COLOR_RGB2BGR)img2 = getImageByUrl(para2)img2 = cv2.cvtColor(np.asarray(img2), cv2.COLOR_RGB2BGR)else:# 通过imread方法直接读取物理路径img1 = cv2.imread(para1)img2 = cv2.imread(para2)hash1 = aHash(img1)hash2 = aHash(img2)n1 = cmpHash(hash1, hash2)print('均值哈希算法相似度aHash：', n1)hash1 = dHash(img1)hash2 = dHash(img2)n2 = cmpHash(hash1, hash2)print('差值哈希算法相似度dHash：', n2)hash1 = pHash(img1)hash2 = pHash(img2)n3 = cmpHash(hash1, hash2)print('感知哈希算法相似度pHash：', n3)n4 = classify_hist_with_split(img1, img2)print('三直方图算法相似度：', n4)n5 = calculate(img1, img2)print("单通道的直方图", n5)print("%d %d %d %.2f %.2f " % (n1, n2, n3, round(n4[0], 2), n5[0]))print("%.2f %.2f %.2f %.2f %.2f " % (1-float(n1/64), 1 -float(n2/64), 1-float(n3/64), round(n4[0], 2), n5[0]))plt.subplot(121)plt.imshow(Image.fromarray(cv2.cvtColor(img1, cv2.COLOR_BGR2RGB)))plt.subplot(122)plt.imshow(Image.fromarray(cv2.cvtColor(img2, cv2.COLOR_BGR2RGB)))plt.show()if __name__ == "__main__":p1="https://ww3.sinaimg.cn/bmiddle/007INInDly1g336j2zziwj30su0g848w.jpg"p2="https://ww2.sinaimg.cn/bmiddle/007INInDly1g336j10d32j30vd0hnam6.jpg"runAllImageSimilaryFun(p1,p2)

# 将图片转化为RGB
def make_regalur_image(img, size=(64, 64)):gray_image = img.resize(size).convert('RGB')return gray_image# 计算直方图
def hist_similar(lh, rh):assert len(lh) == len(rh)hist = sum(1 - (0 if l == r else float(abs(l - r)) / max(l, r)) for l, r in zip(lh, rh)) / len(lh)return hist# 计算相似度
def calc_similar(li, ri):calc_sim = hist_similar(li.histogram(), ri.histogram())return calc_simif __name__ == '__main__':image1 = Image.open('123.jpg')image1 = make_regalur_image(image1)image2 = Image.open('456.jpg')image2 = make_regalur_image(image2)print("图片间的相似度为", calc_similar(image1, image2))

# -*- coding: utf-8 -*-
from skimage.measure import compare_ssim
from scipy.misc import imread
import numpy as np
# 读取图片
img1 = imread('../dataset/100002.png')
img2 = imread('../dataset/100001.png')
img2 = np.resize(img2, (img1.shape[0], img1.shape[1], img1.shape[2]))
print(img1.shape)
print(img2.shape)
ssim =  compare_ssim(img1, img2, multichannel = True)
print(ssim)

from sklearn import metrics as mr
from scipy.misc import imread
import numpy as npimg1 = imread('1.jpg')
img2 = imread('2.jpg')img2 = np.resize(img2, (img1.shape[0], img1.shape[1], img1.shape[2]))img1 = np.reshape(img1, -1)
img2 = np.reshape(img2, -1)
print(img2.shape)
print(img1.shape)
mutual_infor = mr.mutual_info_score(img1, img2)print(mutual_infor)