OpenCV+python计算机视觉图像处理6——刷脸识别

最简单的图片爬虫

# 1.URL 2.html src 3.img 4.img url

import urllib
import urllib3
import os
from bs4 import BeautifulSoup
#load url
html = urllib.request.urlopen('https://class.imooc.com/?c=ios&mc_marking=286b51b2a8e40915ea9023c821882e74&mc_channel=L5').read()
#parse url data (1.html 2.参数 3.'utf-8') 
soup = BeautifulSoup(html,'html.parser',from_encoding='utf-8')
#img
images = soup.findAll('div','img-con')
print(images)
imageName = 0
for image in images:
    link = image.get('style')
    link = 'http:'+link[21:-1]
    print('link=',link)
    
     '''fileFormat = link[-3:]
    if fileFormat == 'png' or fileFormat == 'jpg':
        fileSavePath = 'E:/code/OpenCV/img/'+str(imageName)+'.jpg'
        imageName = imageName + 1
        urllib.request.urlretrieve(link,fileSavePath)'''
    
    if link[-3:] == 'jpg':
        fileSavePath = 'E:/code/OpenCV/img/'+str(imageName)+'.jpg'
        imageName = imageName + 1
        urllib.request.urlretrieve(link,fileSavePath)

OpenCV预处理

# 1.load xml  2.load jpg  3.haar gray 4.detect 5.draw
import cv2
import numpy as np
#load xml (file name)
face_xml = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_xml = cv2.CascadeClassifier('haarcascade_eye.xml')
#load jpg
img = cv2.imread('face.jpg')
cv2.imshow('src',img)
#haar gray
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#detect faces (1.data 2.缩放系数scale 3.人脸不小于5个像素)
faces = face_xml.detectMultiScale(gray,1.3,5)
print('face=',len(faces))
#draw 
index = 0
for (x,y,w,h) in faces:
    cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    roi_face = gray[y:y+h,x:x+w]
    roi_color = img[y:y+h,x:x+w]
    fileName = str(index)+'.jpg'
    cv2.imwrite(fileName,roi_color)
    index = index + 1
    # 1 gray
    eyes = eye_xml.detectMultiScale(roi_face)
    print('eye=',len(eyes))
    #for (e_x,e_y,e_w,e_h) in eyes:
     #   cv2.rectangle(roi_color,(e_x,e_y),(e_x+e_w,e_y+e_h),(0,255,0),2)
cv2.imshow('dst',img)
cv2.waitKey(0)

“某个人脸”识别

# 1.load yale data 
# 2.prepare train label
# 3.cnn
# 4.test

import tensorflow.compat.v1 as tf
import numpy as np
import scipy.io as sio

f = open('Yale_64x64.mat','rb')
mdict = sio.loadmat(f)   #key:fea value:gnd
train_data = mdict['fea']
train_label = mdict['gnd']

train_data = np.random.permutation(train_data)
train_label = np.random.permutation(train_label)
test_data = train_data[0:64]
test_label = train_label[0:64]
np.random.seed(100)
test_data = np.random.permutation(test_data)
np.random.seed(100)
test_label = np.random.permutation(test_label)

#train
train_data = train_data.reshape(train_data.shape[0],64,64,1).astype(np.float32)/255  #归一化
train_label_new = np.zeros([165,15])  #165images 15person
for i in range(0,165):
    j = int(train_label[i,0])-1
    train_label_new[i,j] = 1

test_data_input = test_data.reshape(test_data.shape[0],64,64,1).astype(np.float32)/255
test_label_input = np.zeros([64,15])
for i in range(0,64):
    j = int(test_label[i,0])-1
    test_label_input[i,j] = 1

#cnn acc
tf.disable_v2_behavior()
data_input = tf.placeholder(tf.float32,[None,64,64,1])
label_input = tf.placeholder(tf.float32,[None,15])

layer1 = tf.layers.conv2d(inputs=data_input,filters=32,kernel_size=2,strides=1,padding='SAME',activation=tf.nn.relu)
layer1_pool = tf.layers.max_pooling2d(layer1,pool_size=2,strides=2)
layer2 = tf.reshape(layer1_pool,[-1,32*32*32])
layer2_relu = tf.layers.dense(layer2,1024,tf.nn.relu)
output = tf.layers.dense(layer2_relu,15)


loss = tf.losses.softmax_cross_entropy(onehot_labels=label_input,logits=output)
train = tf.train.GradientDescentOptimizer(0.01).minimize(loss)
accuracy = tf.metrics.accuracy(labels=tf.argmax(label_input,axis=1),predictions=tf.argmax(output,axis=1))[1]

# run acc
init = tf.group(tf.global_variables_initializer(),tf.local_variables_initializer())

with tf.Session() as sess:
    sess.run(init)
    for i in range(0,200):
        train_data_input = np.array(train_data)
        train_label_input = np.array(train_label_new)
        sess.run([train,loss],feed_dict = {
     data_input:train_data_input,label_input:train_label_input})
        acc = sess.run(accuracy,feed_dict={
     data_input:test_data_input,label_input:test_label_input})
        print('acc:%.2f',acc)