Python realize an image analysis [calculated cosine similarity, statistics, histograms, channel, hash, the SSIM other similarity implemented method]

      Recently doing work there need a place to go to compute the similarity between the given different image, the image is on its essence is a 3-dimensional matrix of RGB data, know this feature in the future, a lot of similarity calculation method gradually being proposed and implemented, and here I realized for specific applications to name a few similarity calculation methods I used, the following is a specific code to achieve:

#!usr/bin/env python
#encoding:utf-8
from __future__ import division

 
'''
__Author__:沂水寒城
功能： 图片相似度计算方法集合
       《python实现常用的相似度计算方法》可以看我之前的文章：
       https://yishuihancheng.blog.csdn.net/article/details/89927608
       里面有常用相似度计算方法的原理讲解与代码实现
'''

import os
import cv2
import sys
import numpy as np
from numpy import *
from PIL import Image
from sklearn import metrics
from matplotlib import pyplot as plt
from skimage.measure import compare_ssim
from scipy.stats import pearsonr,spearmanr,kendalltau
 
 
if sys.version_info==2:
    reload(sys)
    sys.setdefaultencoding('utf-8')
 



def image2Vector(img):
    '''
    图像向量化处理
    '''
    vec_list=[]
    for i in range(3):
        for one in img[i].tolist():
            vec_list+=[O/255 for O in one]
    return vec_list


def pearsonrSimilarity(image1, image2):