# 0 前言

🔥 这两年开始毕业设计和毕业答辩的要求和难度不断提升，传统的毕设题目缺少创新和亮点，往往达不到毕业答辩的要求，这两年不断有学弟学妹告诉学长自己做的项目系统达不到老师的要求。

🚩 深度学习 机器视觉 人脸识别系统

🥇学长这里给一个题目综合评分(每项满分5分)

• 难度系数：3分
• 工作量：3分
• 创新点：3分

🧿 选题指导, 项目分享：

# 1 机器学习-人脸识别过程

• 人脸检测
• 人脸对其
• 人脸特征向量化
• 人脸识别

## 人脸特征向量化

PCA人脸特征向量降维示例代码：

``````#coding:utf-8
from numpy import *
from numpy import linalg as la
import cv2
import os

FaceMat = mat(zeros((15,98*116)))
j =0
for i in os.listdir(add):
if i.split('.')[1] == 'normal':
try:
except:
print 'load %s failed'%i
FaceMat[j,:] = mat(img).flatten()
j += 1
return FaceMat

def ReconginitionVector(selecthr = 0.8):
# step1: load the face image data ,get the matrix consists of all image
# step2: average the FaceMat
avgImg = mean(FaceMat,1)
# step3: calculate the difference of avgimg and all image data(FaceMat)
diffTrain = FaceMat-avgImg
#step4: calculate eigenvector of covariance matrix (because covariance matrix will cause memory error)
eigvals,eigVects = linalg.eig(mat(diffTrain.T*diffTrain))
eigSortIndex = argsort(-eigvals)
for i in xrange(shape(FaceMat)[1]):
if (eigvals[eigSortIndex[:i]]/eigvals.sum()).sum() >= selecthr:
eigSortIndex = eigSortIndex[:i]
break
covVects = diffTrain * eigVects[:,eigSortIndex] # covVects is the eigenvector of covariance matrix
# avgImg 是均值图像，covVects是协方差矩阵的特征向量，diffTrain是偏差矩阵
return avgImg,covVects,diffTrain

def judgeFace(judgeImg,FaceVector,avgImg,diffTrain):
diff = judgeImg.T - avgImg
weiVec = FaceVector.T* diff
res = 0
resVal = inf
for i in range(15):
TrainVec = FaceVector.T*diffTrain[:,i]
if  (array(weiVec-TrainVec)**2).sum() < resVal:
res =  i
resVal = (array(weiVec-TrainVec)**2).sum()
return res+1

if __name__ == '__main__':

avgImg,FaceVector,diffTrain = ReconginitionVector(selecthr = 0.9)
nameList = ['01','02','03','04','05','06','07','08','09','10','11','12','13','14','15']

for c in characteristic:

count = 0
for i in range(len(nameList)):

if judgeFace(mat(judgeImg).flatten(),FaceVector,avgImg,diffTrain) == int(nameList[i]):
count += 1
print 'accuracy of %s is %f'%(c, float(count)/len(nameList))  # 求出正确率
``````

## 人脸识别

``````from __future__ import print_function

from time import time
import logging
import matplotlib.pyplot as plt

from sklearn.cross_validation import train_test_split
from sklearn.datasets import fetch_lfw_people
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import RandomizedPCA
from sklearn.svm import SVC

print(__doc__)

# Display progress logs on stdout
logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')

###############################################################################
# Download the data, if not already on disk and load it as numpy arrays

lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)

# introspect the images arrays to find the shapes (for plotting)
n_samples, h, w = lfw_people.images.shape

# for machine learning we use the 2 data directly (as relative pixel
# positions info is ignored by this model)
X = lfw_people.data
n_features = X.shape[1]

# the label to predict is the id of the person
y = lfw_people.target
target_names = lfw_people.target_names
n_classes = target_names.shape[0]

print("Total dataset size:")
print("n_samples: %d" % n_samples)
print("n_features: %d" % n_features)
print("n_classes: %d" % n_classes)

###############################################################################
# Split into a training set and a test set using a stratified k fold

# split into a training and testing set
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25, random_state=42)

###############################################################################
# Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled
# dataset): unsupervised feature extraction / dimensionality reduction
n_components = 80

print("Extracting the top %d eigenfaces from %d faces"
% (n_components, X_train.shape[0]))
t0 = time()
pca = RandomizedPCA(n_components=n_components, whiten=True).fit(X_train)
print("done in %0.3fs" % (time() - t0))

eigenfaces = pca.components_.reshape((n_components, h, w))

print("Projecting the input data on the eigenfaces orthonormal basis")
t0 = time()
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
print("done in %0.3fs" % (time() - t0))

###############################################################################
# Train a SVM classification model

print("Fitting the classifier to the training set")
t0 = time()
param_grid = {'C': [1,10, 100, 500, 1e3, 5e3, 1e4, 5e4, 1e5],
'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)
clf = clf.fit(X_train_pca, y_train)
print("done in %0.3fs" % (time() - t0))
print("Best estimator found by grid search:")
print(clf.best_estimator_)

print(clf.best_estimator_.n_support_)
###############################################################################
# Quantitative evaluation of the model quality on the test set

print("Predicting people's names on the test set")
t0 = time()
y_pred = clf.predict(X_test_pca)
print("done in %0.3fs" % (time() - t0))

print(classification_report(y_test, y_pred, target_names=target_names))
print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))

###############################################################################
# Qualitative evaluation of the predictions using matplotlib

def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
"""Helper function to plot a gallery of portraits"""
plt.figure(figsize=(1.8 * n_col, 2.4 * n_row))
plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)
for i in range(n_row * n_col):
plt.subplot(n_row, n_col, i + 1)
# Show the feature face
plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray)
plt.title(titles[i], size=12)
plt.xticks(())
plt.yticks(())

# plot the result of the prediction on a portion of the test set

def title(y_pred, y_test, target_names, i):
pred_name = target_names[y_pred[i]].rsplit(' ', 1)[-1]
true_name = target_names[y_test[i]].rsplit(' ', 1)[-1]
return 'predicted: %sntrue:      %s' % (pred_name, true_name)

prediction_titles = [title(y_pred, y_test, target_names, i)
for i in range(y_pred.shape[0])]

plot_gallery(X_test, prediction_titles, h, w)

# plot the gallery of the most significative eigenfaces

eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)

plt.show()
``````

# 2 深度学习-人脸识别过程

• 人脸检测
• 人脸对其
• 人脸识别

## 人脸识别

#### Metric Larning

Contrastive loss不仅考虑了相同类别的距离最小化，也同时考虑了不同类别的距离最大化，通过充分运用训练样本的label信息提升人脸识别的准确性。因此，该loss函数本质上使得同一个人的照片在特征空间距离足够近，不同人在特征空间里相距足够远直到超过某个阈值。(听起来和triplet loss有点像)。

THE END