def similarity_mode_2(self, image1, image2):
"""
直方图的距离计算
:param image1:
:param image2:
:return:
"""
# 预处理
img1 = image1.resize((256, 256)).convert('RGB')
img2 = image2.resize((256, 256)).convert('RGB')
sim = image_similarity_fundimental.difference(img1.histogram(),
img2.histogram())
return sim
def similarity_mode_3(self, image1, image2):
"""
感知哈希算法
:param image1:
:param image2:
:return:
"""
# 如果是frame的话，可以直接使用
# img = cv2.resize(frame, (8, 8))
img1 = image1.resize((128, 128)).convert('1')
img2 = image2.resize((128, 128)).convert('1')
hist1 = list(img1.getdata())
hist2 = list(img2.getdata())
sim = image_similarity_fundimental.difference(hist1, hist2)
return sim
def similarity_mode_1(self, image1, image2):
"""
分块直方图的距离计算
:param image1:
:param image2:
:return:
"""
sum = 0
img1 = image1.resize((256, 256)).convert('RGB')
img2 = image2.resize((256, 256)).convert('RGB')
for i in range(4):
for j in range(4):
hist1 = img1.crop((i * 64, j * 64, i * 64 + 63,
j * 64 + 63)).copy().histogram()
hist2 = img2.crop((i * 64, j * 64, i * 64 + 63,
j * 64 + 63)).copy().histogram()
sum += image_similarity_fundimental.difference(hist1, hist2)
# print difference(hist1, hist2)
return sum / 16
def similary_calculate(self, img1, img2):
hist1 = list(img1.getdata())
hist2 = list(img2.getdata())
return image_similarity_fundimental.difference(hist1, hist2)