Python 五种图片相似度比较方法
·
均值哈希算法
# -*- coding: utf-8 -*-
import cv2
import numpy as np
# Hash值对比
def cmpHash(hash1, hash2,shape=(10,10)):
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)):
# 相等则n计数+1,n最终为相似度
if hash1[i] == hash2[i]:
n = n + 1
return n/(shape[0]*shape[1])
# 均值哈希算法
def aHash(img,shape=(10,10)):
# 缩放为10*10
img = cv2.resize(img, shape)
# 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 = 0
hash_str = ''
# 遍历累加求像素和
for i in range(shape[0]):
for j in range(shape[1]):
s = s + gray[i, j]
# 求平均灰度
avg = s / 100
# 灰度大于平均值为1相反为0生成图片的hash值
for i in range(shape[0]):
for j in range(shape[1]):
if gray[i, j] > avg:
hash_str = hash_str + '1'
else:
hash_str = hash_str + '0'
return hash_str
def main():
img1 = cv2.imread('328/0003.jpg')
img2 = cv2.imread('328/0004.jpg')
hash1 = aHash(img1)
hash2 = aHash(img2)
n = cmpHash(hash1, hash2)
print('均值哈希算法相似度:', n)
if __name__=="__main__":
main()
说明:
首先,将一张图片大小调整为10x10,然后转化为灰度图。
接着,求出平均灰度,大于平均灰度值更改为1,反之为0,生成哈希值。
随后,对比两个图片矩阵的相似度,最后返回相似百分比
差值哈希算法
# -*- coding: utf-8 -*-
import cv2
import numpy as np
# Hash值对比
def cmpHash(hash1, hash2,shape=(10,10)):
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)):
# 相等则n计数+1,n最终为相似度
if hash1[i] == hash2[i]:
n = n + 1
return n/(shape[0]*shape[1])
# 差值感知算法
def dHash(img,shape=(10,10)):
# 缩放10*11
img = cv2.resize(img, (shape[0]+1, shape[1]))
# 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(shape[0]):
for j in range(shape[1]):
if gray[i, j] > gray[i, j + 1]:
hash_str = hash_str + '1'
else:
hash_str = hash_str + '0'
return hash_str
def main():
img1 = cv2.imread('328/0003.jpg')
img2 = cv2.imread('328/0004.jpg')
hash1 = dHash(img1)
hash2 = dHash(img2)
n = cmpHash(hash1, hash2)
print('均值哈希算法相似度:', n)
if __name__=="__main__":
main()
说明:
首先,将一张图片大小调整为10x11,然后转化为灰度图。
接着,比较每行当前值与相邻的下一个值的大小。如果当前值比较大,灰度值更改为1,反之为0,生成哈希值。。
随后,对比两个图片矩阵的相似度,最后返回相似百分比
感知哈希算法
# -*- coding: utf-8 -*-
import cv2
import numpy as np
# Hash值对比
def cmpHash(hash1, hash2,shape=(10,10)):
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)):
# 相等则n计数+1,n最终为相似度
if hash1[i] == hash2[i]:
n = n + 1
return n/(shape[0]*shape[1])
# 感知哈希算法(pHash)
def pHash(img,shape=(10,10)):
# 缩放32*32
img = 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[0:10, 0:10]
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 hash
def main():
img1 = cv2.imread('328/0003.jpg')
img2 = cv2.imread('328/0004.jpg')
hash1 = pHash(img1)
hash2 = pHash(img2)
n = cmpHash(hash1, hash2)
print('感知哈希算法相似度:', n)
if __name__=="__main__":
main()
说明:
首先,将一张图片大小调整为32x32,然后转化为灰度图,进行离散余弦变换(dct)变换。
接着,opencv实现10x10掩码操作,并求出掩码区域均值,掩码区域像素值大于平均值掩码区域矩阵值设为1,反之为0。
随后,对比两个图片矩阵的相似度,最后返回相似百分比
三直方图算法相似度
# -*- coding: utf-8 -*-
import cv2
import numpy as np
# 通过得到RGB每个通道的直方图来计算相似度
def classify_hist_with_split(image1, image2, size=(256, 256)):
# 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 = 0
for im1, im2 in zip(sub_image1, sub_image2):
sub_data += calculate(im1, im2)
sub_data = sub_data / 3
return sub_data
# 计算单通道的直方图的相似值
def calculate(image1, image2):
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 main():
img1 = cv2.imread('328/0003.jpg')
img2 = cv2.imread('328/0004.jpg')
n = classify_hist_with_split(img1, img2)
print('三直方图算法相似度:', n[0])
if __name__=="__main__":
main()
说明:
首先,将一张图片大小调整为256x256,并分离出rgb三个通道数组。
接着,使用图像直方图的函数,直方图均衡化,计算出0-255的数值
随后,对比两个图片直方图的重合度,最后返回相似百分比
单通道的直方图算法
# -*- coding: utf-8 -*-
import cv2
import numpy as np
# 计算单通道的直方图的相似值
def calculate(image1, image2):
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 main():
img1 = cv2.imread('328/0003.jpg')
img2 = cv2.imread('328/0004.jpg')
n = calculate(img1, img2)
print('单通道的直方图算法相似度:', n[0])
if __name__=="__main__":
main()
说明:
首先,输入一张图片,使用rgb三个通道的某一个通道。
接着,使用图像直方图的函数,直方图均衡化,计算出0-255的数值
随后,对比两个图片直方图的重合度,最后返回相似百分比
全部代码
# -*- coding: utf-8 -*-
import cv2
import numpy as np
# 均值哈希算法
def aHash(img,shape=(10,10)):
# 缩放为10*10
img = cv2.resize(img, shape)
# 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 = 0
hash_str = ''
# 遍历累加求像素和
for i in range(shape[0]):
for j in range(shape[1]):
s = s + gray[i, j]
# 求平均灰度
avg = s / 100
# 灰度大于平均值为1相反为0生成图片的hash值
for i in range(shape[0]):
for j in range(shape[1]):
if gray[i, j] > avg:
hash_str = hash_str + '1'
else:
hash_str = hash_str + '0'
return hash_str
# 差值感知算法
def dHash(img,shape=(10,10)):
# 缩放10*11
img = cv2.resize(img, (shape[0]+1, shape[1]))
# 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(shape[0]):
for j in range(shape[1]):
if gray[i, j] > gray[i, j + 1]:
hash_str = hash_str + '1'
else:
hash_str = hash_str + '0'
return hash_str
# 感知哈希算法(pHash)
def pHash(img,shape=(10,10)):
# 缩放32*32
img = 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[0:10, 0:10]
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 hash
# 通过得到RGB每个通道的直方图来计算相似度
def classify_hist_with_split(image1, image2, size=(256, 256)):
# 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 = 0
for im1, im2 in zip(sub_image1, sub_image2):
sub_data += calculate(im1, im2)
sub_data = sub_data / 3
return sub_data
# 计算单通道的直方图的相似值
def calculate(image1, image2):
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
# Hash值对比
def cmpHash(hash1, hash2,shape=(10,10)):
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)):
# 相等则n计数+1,n最终为相似度
if hash1[i] == hash2[i]:
n = n + 1
return n/(shape[0]*shape[1])
def main():
img1 = cv2.imread('328/0003.jpg')
img2 = cv2.imread('328/0004.jpg')
hash1 = aHash(img1)
hash2 = aHash(img2)
n = cmpHash(hash1, hash2)
print('均值哈希算法相似度:', n)
hash1 = dHash(img1)
hash2 = dHash(img2)
n = cmpHash(hash1, hash2)
print('差值哈希算法相似度:', n)
hash1 = pHash(img1)
hash2 = pHash(img2)
n = cmpHash(hash1, hash2)
print('感知哈希算法相似度:', n)
n = classify_hist_with_split(img1, img2)
print('三直方图算法相似度:', n[0])
n = calculate(img1, img2)
print('单通道的直方图算法相似度:', n[0])
if __name__=="__main__":
main()
#经测试均值哈希算法与三直方图算法相似度效果较好
参考,https://blog.csdn.net/enter89/article/details/90293971
更多推荐
已为社区贡献1条内容
所有评论(0)