梯度直方图特征、phash特征的k-means聚类以及层次聚类

《将图片转化为向量并使用K-means进行聚类》

https://blog.csdn.net/gusui7202/article/details/88081072

使用了原始图像数据进行聚类，现在先提取图像的特征然后再进行聚类。

首先使用的是梯度直方图特征，代码如下：主要还是修改地址和聚类数目

#!/usr/bin/python
# coding=utf-8
'''
基于直方图特征的图片聚类实现
'''
import numpy as np
import os
from PIL import Image
#coding=utf-8
from numpy import *

def loadDataSet(fileName):
    dataMat = []
    fr = open(fileName)
    for line in fr.readlines():
        curLine = line.strip().split('\t')
        fltLine = map(float, curLine)
        dataMat.append(fltLine)
    return dataMat
    
#计算两个向量的距离，用的是欧几里得距离
def distEclud(vecA, vecB):
    return np.sqrt(sum(np.power(vecA - vecB, 2)))

#随机生成初始的质心（ng的课说的初始方式是随机选K个点）    
def randCent(dataSet, k):
    n = np.shape(dataSet)[1]
    centroids = np.mat(np.zeros((k,n)))
    for j in range(n):
        minJ = min(dataSet[:,j])
        rangeJ = float(max(np.array(dataSet)[:,j]) - minJ)
        centroids[:,j] = minJ + rangeJ * np.random.rand(k,1)
    return centroids
    
def kMeans(dataSet, k, distMeas=distEclud, createCent=randCent):
    m =np.shape(dataSet)[0]
    clusterAssment = np.mat(np.zeros((m,2)))#create mat to assign data points 
                                      #to a centroid, also holds SE of each point
    centroids = createCent(dataSet, k)
    clusterChanged = True
    while clusterChanged:
        clusterChanged = False
        for i in range(m):#for each data point assign it to the closest centroid
            minDist = np.inf
            minIndex = -1
            for j in range(k):
                distJI = distMeas(centroids[j,:],dataSet[i,:])
                if distJI < minDist:
                    minDist = distJI; minIndex = j
            if clusterAssment[i,0] != minIndex: 
                clusterChanged = True
            clusterAssment[i,:] = minIndex,minDist**2
        #print centroids
        for cent in range(k):#recalculate centroids
            ptsInClust = dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]#get all the point in this cluster
            centroids[cent,:] = mean(ptsInClust, axis=0) #assign centroid to mean 
    return centroids, clusterAssment
    
def show(dataSet, k, centroids, clusterAssment):
    from matplotlib import pyplot as plt  
    numSamples, dim = dataSet.shape  
    mark = ['or', 'ob', 'og', 'ok', '^r', '+r', 'sr', 'dr'