import os
from numpy import *
import numpy as np
import cv2
import matplotlib.pyplot as plt
from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['SimHei']
def img2vector(image):
img=cv2.imread(image,0)
rows,cols=img.shape
imgVector = np.zeros((1,rows*cols))
imgVector = np.reshape(img,(1,rows*cols))
return imgVector
img2vector('1.pgm').shape
orlpath="C://Users//Hasee//Desktop//orl_faces"
def load_orl(k):
'''
对训练数据集进行数组初始化,用0填充,每张图片尺寸都定为112*92,
现在共有40个人,每个人都选择k张,则整个训练集大小为40*k,112*92
'''
train_face=np.zeros((40*k,112*92))
train_label=np.zeros(40*k)
test_face=np.zeros((40*(10-k),112*92))
test_label=np.zeros(40*(10-k))
sample=random.permutation(10)+1
for i in range(40):
people_num=i+1
for j in range(10):
image=orlpath+'/s'+str(people_num)+'/'+str(sample[j])+'.pgm'
img=img2vector(image)
if j<k:
train_face[i*k+j,:] = img
train_label[i*k+j] =people_num
else:
test_face[i*(10-k)+(j-k),:] = img
test_label[i*(10-k)+(j-k)] = people_num
return train_face,train_label,test_face,test_label
def PCA(data,r):
data=np.float32(np.mat(data))
rows,cols=np.shape(data)
data_mean=np.mean(data,0)
A=data-np.tile(data_mean,(rows,1))
C=A*A.T
D,V=np.linalg.eig(C)
V_r=V[:,0:r]
V_r=A.T*V_r
for i in range(r):
V_r[:,i]=V_r[:,i]/np.linalg.norm(V_r[:,i])
final_data=A*V_r
return final_data,data_mean,V_r
def face_rec():
for r in range(10,41,10):
print("当降维到%d时"%(r))
x_value=[]
y_value=[]
for k in range(1,10):
train_face,train_label,test_face,test_label=load_orl(k)
data_train_new,data_mean,V_r=PCA(train_face,r)
num_train = data_train_new.shape[0]
num_test = test_face.shape[0]
temp_face = test_face - np.tile(data_mean,(num_test,1))
data_test_new = temp_face*V_r
data_test_new = np.array(data_test_new)
data_train_new = np.array(data_train_new)
true_num = 0
for i in range(num_test):
testFace = data_test_new[i,:]
diffMat = data_train_new - np.tile(testFace,(num_train,1))
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
sortedDistIndicies = sqDistances.argsort()
indexMin = sortedDistIndicies[0]
if train_label[indexMin] == test_label[i]:
true_num += 1
else:
pass
accuracy = float(true_num)/num_test
x_value.append(k)
y_value.append(round(accuracy,2))
print ('当每个人选择%d张照片进行训练时,The classify accuracy is: %.2f%%'%(k,accuracy * 100))