#encoding=utf-8 
import numpy as np 
import cv2 
import os 
 
class EigenFace(object): 
 def __init__(self,threshold,dimNum,dsize): 
 self.threshold = threshold # 閾值暫未使用 
 self.dimNum = dimNum 
 self.dsize = dsize 
 
 def loadImg(self,fileName,dsize): 
 ''''' 
 載入圖像，灰度化處理，統(tǒng)一尺寸，直方圖均衡化 
 :param fileName: 圖像文件名 
 :param dsize: 統(tǒng)一尺寸大小。元組形式 
 :return: 圖像矩陣 
 ''' 
 img = cv2.imread(fileName) 
 retImg = cv2.resize(img,dsize) 
 retImg = cv2.cvtColor(retImg,cv2.COLOR_RGB2GRAY) 
 retImg = cv2.equalizeHist(retImg) 
 # cv2.imshow('img',retImg) 
 # cv2.waitKey() 
 return retImg 
 
 
 def createImgMat(self,dirName): 
 ''''' 
 生成圖像樣本矩陣，組織形式為行為屬性，列為樣本 
 :param dirName: 包含訓練數(shù)據(jù)集的圖像文件夾路徑 
 :return: 樣本矩陣，標簽矩陣 
 ''' 
 dataMat = np.zeros((10,1)) 
 label = [] 
 for parent,dirnames,filenames in os.walk(dirName): 
  # print parent 
  # print dirnames 
  # print filenames 
  index = 0 
  for dirname in dirnames: 
  for subParent,subDirName,subFilenames in os.walk(parent+'/'+dirname): 
   for filename in subFilenames: 
   img = self.loadImg(subParent+'/'+filename,self.dsize) 
   tempImg = np.reshape(img,(-1,1)) 
   if index == 0 : 
    dataMat = tempImg 
   else: 
    dataMat = np.column_stack((dataMat,tempImg)) 
   label.append(subParent+'/'+filename) 
   index += 1 
 return dataMat,label 
 
 
 def PCA(self,dataMat,dimNum): 
 ''''' 
 PCA函數(shù)，用于數(shù)據(jù)降維 
 :param dataMat: 樣本矩陣 
 :param dimNum: 降維后的目標維度 
 :return: 降維后的樣本矩陣和變換矩陣 
 ''' 
 # 均值化矩陣 
 meanMat = np.mat(np.mean(dataMat,1)).T 
 print '平均值矩陣維度',meanMat.shape 
 diffMat = dataMat-meanMat 
 # 求協(xié)方差矩陣，由于樣本維度遠遠大于樣本數(shù)目，所以不直接求協(xié)方差矩陣，采用下面的方法 
 covMat = (diffMat.T*diffMat)/float(diffMat.shape[1]) # 歸一化 
 #covMat2 = np.cov(dataMat,bias=True) 
 #print '基本方法計算協(xié)方差矩陣為',covMat2 
 print '協(xié)方差矩陣維度',covMat.shape 
 eigVals, eigVects = np.linalg.eig(np.mat(covMat)) 
 print '特征向量維度',eigVects.shape 
 print '特征值',eigVals 
 eigVects = diffMat*eigVects 
 eigValInd = np.argsort(eigVals) 
 eigValInd = eigValInd[::-1] 
 eigValInd = eigValInd[:dimNum] # 取出指定個數(shù)的前n大的特征值 
 print '選取的特征值',eigValInd 
 eigVects = eigVects/np.linalg.norm(eigVects,axis=0) #歸一化特征向量 
 redEigVects = eigVects[:,eigValInd] 
 print '選取的特征向量',redEigVects.shape 
 print '均值矩陣維度',diffMat.shape 
 lowMat = redEigVects.T*diffMat 
 print '低維矩陣維度',lowMat.shape 
 return lowMat,redEigVects 
 
 def compare(self,dataMat,testImg,label): 
 ''''' 
 比較函數(shù)，這里只是用了最簡單的歐氏距離比較，還可以使用KNN等方法，如需修改修改此處即可 
 :param dataMat: 樣本矩陣 
 :param testImg: 測試圖像矩陣，最原始形式 
 :param label: 標簽矩陣 
 :return: 與測試圖片最相近的圖像文件名 
 ''' 
 testImg = cv2.resize(testImg,self.dsize) 
 testImg = cv2.cvtColor(testImg,cv2.COLOR_RGB2GRAY) 
 testImg = np.reshape(testImg,(-1,1)) 
 lowMat,redVects = self.PCA(dataMat,self.dimNum) 
 testImg = redVects.T*testImg 
 print '檢測樣本變換后的維度',testImg.shape 
 disList = [] 
 testVec = np.reshape(testImg,(1,-1)) 
 for sample in lowMat.T: 
  disList.append(np.linalg.norm(testVec-sample)) 
 print disList 
 sortIndex = np.argsort(disList) 
 return label[sortIndex[0]] 
 
 
 def predict(self,dirName,testFileName): 
 ''''' 
 預測函數(shù) 
 :param dirName: 包含訓練數(shù)據(jù)集的文件夾路徑 
 :param testFileName: 測試圖像文件名 
 :return: 預測結(jié)果 
 ''' 
 testImg = cv2.imread(testFileName) 
 dataMat,label = self.createImgMat(dirName) 
 print '加載圖片標簽',label 
 ans = self.compare(dataMat,testImg,label) 
 return ans 
 
 
if __name__ == '__main__': 
 eigenface = EigenFace(20,50,(50,50)) 
 print eigenface.predict('d:/face','D:/face_test/1.bmp')