CNN卷積神經網絡人臉識別

圖片總共40我的，每人10張圖片，每張圖片高57，寬47。共400張圖片。

讀取圖片的py文件

import numpy
import pandas
from PIL import Image
from keras import backend as K
from keras.utils import np_utils


"""
加載圖像數據的函數,dataset_path即圖像olivettifaces的路徑
加載olivettifaces後，劃分爲train_data,valid_data,test_data三個數據集
函數返回train_data,valid_data,test_data以及對應的label
"""

# 400個樣本，40我的，每人10張樣本圖。每張樣本圖高57*寬47，須要2679個像素點。每一個像素點作了歸一化處理
def load_data(dataset_path):
img = Image.open(dataset_path)
img_ndarray = numpy.asarray(img, dtype='float64') / 256
print(img_ndarray.shape)
faces = numpy.empty((400,57,47))
for row in range(20):
for column in range(20):
faces[row * 20 + column] = img_ndarray[row * 57:(row + 1) * 57, column * 47:(column + 1) * 47]
# 設置400個樣本圖的標籤
label = numpy.empty(400)
for i in range(40):
label[i * 10:i * 10 + 10] = i
label = label.astype(numpy.int)
label = np_utils.to_categorical(label, 40) # 將40分類類標號轉化爲one-hot編碼

# 分紅訓練集、驗證集、測試集，大小以下
train_data = numpy.empty((320, 57,47)) # 320個訓練樣本
train_label = numpy.empty((320,40)) # 320個訓練樣本，每一個樣本40個輸出機率
valid_data = numpy.empty((40, 57,47)) # 40個驗證樣本
valid_label = numpy.empty((40,40)) # 40個驗證樣本，每一個樣本40個輸出機率
test_data = numpy.empty((40, 57,47)) # 40個測試樣本
test_label = numpy.empty((40,40)) # 40個測試樣本，每一個樣本40個輸出機率

for i in range(40):
train_data[i * 8:i * 8 + 8] = faces[i * 10:i * 10 + 8]
train_label[i * 8:i * 8 + 8] = label[i * 10:i * 10 + 8]
valid_data[i] = faces[i * 10 + 8]
valid_label[i] = label[i * 10 + 8]
test_data[i] = faces[i * 10 + 9]
test_label[i] = label[i * 10 + 9]

return [(train_data, train_label), (valid_data, valid_label),(test_data, test_label)]


if __name__ == '__main__':
[(train_data, train_label), (valid_data, valid_label), (test_data, test_label)] = load_data('olivettifaces.gif')
oneimg = train_data[0]*256
print(oneimg)
im = Image.fromarray(oneimg)
im.show()

 

CNN人臉識別代碼

import numpy as np
np.random.seed(1337) # for reproducibility
from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D,AveragePooling2D
from PIL import Image
import FaceData
# 全局變量 
batch_size = 128 # 批處理樣本數量
nb_classes = 40 # 分類數目
epochs = 600 # 迭代次數
img_rows, img_cols = 57, 47 # 輸入圖片樣本的寬高
nb_filters = 32 # 卷積核的個數
pool_size = (2, 2) # 池化層的大小
kernel_size = (5, 5) # 卷積核的大小
input_shape = (img_rows, img_cols,1) # 輸入圖片的維度

[(X_train, Y_train), (X_valid, Y_valid),(X_test, Y_test)] =FaceData.load_data('olivettifaces.gif')

X_train=X_train[:,:,:,np.newaxis] # 添加一個維度，表明圖片通道。這樣數據集共4個維度，樣本個數、寬度、高度、通道數
X_valid=X_valid[:,:,:,np.newaxis] # 添加一個維度，表明圖片通道。這樣數據集共4個維度，樣本個數、寬度、高度、通道數
X_test=X_test[:,:,:,np.newaxis] # 添加一個維度，表明圖片通道。這樣數據集共4個維度，樣本個數、寬度、高度、通道數

print('樣本數據集的維度：', X_train.shape,Y_train.shape)
print('測試數據集的維度：', X_test.shape,Y_test.shape)


# 構建模型
model = Sequential()
model.add(Conv2D(6,kernel_size,input_shape=input_shape,strides=1)) # 卷積層1
model.add(AveragePooling2D(pool_size=pool_size,strides=2)) # 池化層
model.add(Conv2D(12,kernel_size,strides=1)) # 卷積層2
model.add(AveragePooling2D(pool_size=pool_size,strides=2)) # 池化層
model.add(Flatten()) # 拉成一維數據
model.add(Dense(nb_classes)) # 全鏈接層2
model.add(Activation('sigmoid')) # sigmoid評分

# 編譯模型
model.compile(loss='categorical_crossentropy',optimizer='adadelta',metrics=['accuracy'])
# 訓練模型
model.fit(X_train, Y_train, batch_size=batch_size, epochs=epochs,verbose=1, validation_data=(X_test, Y_test))
# 評估模型
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])

y_pred = model.predict(X_test)
y_pred = y_pred.argmax(axis=1) # 獲取機率最大的分類，獲取每行最大值所在的列
for i in range(len(y_pred)):
oneimg = X_test[i,:,:,0]*256
im = Image.fromarray(oneimg)
im.show()
print('第%d我的識別爲第%d我的'%(i,y_pred[i]))