97 lines
3.3 KiB
Python
97 lines
3.3 KiB
Python
|
## -*- coding: utf-8 -*-
|
|||
|
|
# !/usr/bin/env python
|
|||
|
|
# 余弦相似度计算
|
|||
|
|
import time
|
|||
|
|
|
|||
|
|
import cv2
|
|||
|
|
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 = vectors
|
|||
|
|
a_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
|
|||
|
|
|
|||
|
|
|
|||
|
|
#差值感知算法
|
|||
|
|
def dHash(image):
|
|||
|
|
#缩放9*8
|
|||
|
|
image=cv2.resize(image,(9,8),interpolation=cv2.INTER_CUBIC)
|
|||
|
|
#转换灰度图
|
|||
|
|
image=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
|
|||
|
|
# print(image.shape)
|
|||
|
|
hash=[]
|
|||
|
|
#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 image[i,j]>image[i,j+1]:
|
|||
|
|
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
|
|||
|
|
|
|||
|
|
if __name__ == '__main__':
|
|||
|
|
# 把图片表示成一个向量，通过计算向量之间的余弦距离来表征两张图片的相似度 0.9760
|
|||
|
|
image1 = cv2.imread('../image/1.jpg')
|
|||
|
|
image2 = cv2.imread('../image/2.jpg')
|
|||
|
|
# image3 = cv2.imread('image/AI2.jpg')
|
|||
|
|
# image4 = cv2.imread('image/AI3.jpg')
|
|||
|
|
# image5 = cv2.imread('image/AI4.jpg')
|
|||
|
|
# image6 = cv2.imread('a.jpg')
|
|||
|
|
# image7 = cv2.imread('AI.jpg')
|
|||
|
|
hash1 = dHash(image1)
|
|||
|
|
hash2 = dHash(image2)
|
|||
|
|
# hash3 = dHash(image3)
|
|||
|
|
# hash4 = dHash(image4)
|
|||
|
|
# hash5 = dHash(image5)
|
|||
|
|
# hash6 = dHash(image6)
|
|||
|
|
# hash7 = dHash(image7)
|
|||
|
|
start = time.time()
|
|||
|
|
dist = Hamming_distance(hash1, hash2)
|
|||
|
|
#将距离转化为相似度
|
|||
|
|
similarity = 1 - dist * 1.0 / 64
|
|||
|
|
# print(dist)
|
|||
|
|
print(similarity, time.time() - start)
|
|||
|
|
# cosin = image_similarity_vectors_via_numpy(image1, image2)
|
|||
|
|
# print('图片余弦相似度', cosin)
|
|||
|
|
# cosin1 = image_similarity_vectors_via_numpy(image1, image3)
|
|||
|
|
# print('图片余弦相似度', cosin1)
|
|||
|
|
# cosin2 = image_similarity_vectors_via_numpy(image1, image4)
|
|||
|
|
# print('图片余弦相似度', cosin2)
|
|||
|
|
# cosin3 = image_similarity_vectors_via_numpy(image1, image5)
|
|||
|
|
# print('图片余弦相似度', cosin3)
|
|||
|
|
# cosin4 = image_similarity_vectors_via_numpy(image5, image6)
|
|||
|
|
# print('图片余弦相似度', cosin4)
|
|||
|
|
# cosin5 = image_similarity_vectors_via_numpy(image1, image6)
|
|||
|
|
# print('图片余弦相似度', cosin5)
|