OpenCV与TensorFlow手写数字刷脸识别
title: OpenCV与TensorFlow手写数字刷脸识别
date: 2019-09-03 10:07:47
categories: 人工智能
tags:
- OpenCV
- Tensorflow
cover: https://www.github.com/OneJane/blog/raw/master/小书匠/81cb6cca40c296e1f1baa8ae366a5e58_hd.jpg
OpenCV与TensorFlow手写数字刷脸识别
http://yann.lecun.com/exdb/mnist/
手写数字识别
KNN最近领域
# 1 重要
# 2 KNN最近领域 CNN卷积神经网络 2种
# 3 样本
# 4 旧瓶装新酒 ：数字识别的不同
# 4.1 网络 4。2 每一级 4.3 先原理 后代码
# 本质：knn test 样本 K个 max4 3个1 -》1
# 1 load Data 1.1 随机数 1.2 4组 训练 测试 （图片 和 标签）
# 2 knn test train distance 5*500 = 2500 784=28*28
# 3 knn k个最近的图片5 500 1-》500train （4）
# 4 k个最近的图片-> parse centent label
# 5 label -》 数字 p9 测试图片-》数据
# 6 检测概率统计
import tensorflow as tf
import numpy as np
import random
from tensorflow.examples.tutorials.mnist import input_data
# load data 2 one_hot : 1 0000 1 fileName
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
# 属性设置
trainNum = 55000
testNum = 10000
trainSize = 500
testSize = 5
k = 4
# data 分解 1 trainSize 2范围0-trainNum 3 replace=False
trainIndex = np.random.choice(trainNum,trainSize,replace=False)
testIndex = np.random.choice(testNum,testSize,replace=False)
trainData = mnist.train.images[trainIndex]# 训练图片
trainLabel = mnist.train.labels[trainIndex]# 训练标签
testData = mnist.test.images[testIndex]
testLabel = mnist.test.labels[testIndex]
# 28*28 = 784
print('trainData.shape=',trainData.shape)#500*784 1 图片个数 2 784?
print('trainLabel.shape=',trainLabel.shape)#500*10
print('testData.shape=',testData.shape)#5*784
print('testLabel.shape=',testLabel.shape)#5*10
print('testLabel=',testLabel)# 4 :testData [0] 3:testData[1] 6
# tf input 784->image
trainDataInput = tf.placeholder(shape=[None,784],dtype=tf.float32)
trainLabelInput = tf.placeholder(shape=[None,10],dtype=tf.float32)
testDataInput = tf.placeholder(shape=[None,784],dtype=tf.float32)
testLabelInput = tf.placeholder(shape=[None,10],dtype=tf.float32)
#knn distance 5*785. 5*1*784
# 5测试图片 500训练图片 784 (3D) 2500*784
f1 = tf.expand_dims(testDataInput,1) # 维度扩展
f2 = tf.subtract(trainDataInput,f1)# 784 sum(784)
f3 = tf.reduce_sum(tf.abs(f2),reduction_indices=2)# 完成数据累加 784 abs
# 5*500
f4 = tf.negative(f3)# 取反
f5,f6 = tf.nn.top_k(f4,k=4) # 选取f4 最大的四个值
# f3 最小的四个值
# f6 index->trainLabelInput
f7 = tf.gather(trainLabelInput,f6)
# f8 num reduce_sum reduction_indices=1 '竖直'
f8 = tf.reduce_sum(f7,reduction_indices=1)
# tf.argmax 选取在某一个最大的值 index
f9 = tf.argmax(f8,dimension=1)
# f9 -> test5 image -> 5 num
with tf.Session() as sess:
# f1 <- testData 5张图片
p1 = sess.run(f1,feed_dict={testDataInput:testData[0:5]})
print('p1=',p1.shape)# p1= (5, 1, 784)
p2 = sess.run(f2,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
print('p2=',p2.shape)#p2= (5, 500, 784) (1,100)
p3 = sess.run(f3,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
print('p3=',p3.shape)#p3= (5, 500)
print('p3[0,0]=',p3[0,0]) #130.451 knn distance p3[0,0]= 155.812
p4 = sess.run(f4,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
print('p4=',p4.shape)
print('p4[0,0]',p4[0,0])
p5,p6 = sess.run((f5,f6),feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
#p5= (5, 4) 每一张测试图片（5张）分别对应4张最近训练图片
#p6= (5, 4)
print('p5=',p5.shape)
print('p6=',p6.shape)
print('p5[0,0]',p5[0])
print('p6[0,0]',p6[0])# p6 index
p7 = sess.run(f7,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5],trainLabelInput:trainLabel})
print('p7=',p7.shape)#p7= (5, 4, 10)
print('p7[]',p7)
p8 = sess.run(f8,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5],trainLabelInput:trainLabel})
print('p8=',p8.shape)
print('p8[]=',p8)
p9 = sess.run(f9,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5],trainLabelInput:trainLabel})
print('p9=',p9.shape)
print('p9[]=',p9)
p10 = np.argmax(testLabel[0:5],axis=1)
print('p10[]=',p10)
j = 0
for i in range(0,5):
if p10[i] == p9[i]:
j = j+1
print('ac=',j*100/5)
CNN卷积神经网络
#cnn : 1 卷积
# ABC
# A: 激励函数+矩阵 乘法加法
# A CNN : pool（激励函数+矩阵 卷积 加法）
# C：激励函数+矩阵 乘法加法（A-》B）
# C：激励函数+矩阵 乘法加法（A-》B） + softmax（矩阵 乘法加法）
# loss：tf.reduce_mean(tf.square(y-layer2))
# loss：code
#1 import
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
# 2 load data
mnist = input_data.read_data_sets('MNIST_data',one_hot = True)
# 3 input
imageInput = tf.placeholder(tf.float32,[None,784]) # 28*28
labeInput = tf.placeholder(tf.float32,[None,10]) # 10 列数
# 4 data reshape
# [None,784]->M*28*28*1 2D->4D 28*28 wh 1 channel
imageInputReshape = tf.reshape(imageInput,[-1,28,28,1])
# 5 卷积 w0 : 卷积内核 5*5 out:32 in:1
w0 = tf.Variable(tf.truncated_normal([5,5,1,32],stddev = 0.1))
b0 = tf.Variable(tf.constant(0.1,shape=[32]))
# 6 # layer1：激励函数+卷积运算
# imageInputReshape : M*28*28*1 w0:5,5,1,32
layer1 = tf.nn.relu(tf.nn.conv2d(imageInputReshape,w0,strides=[1,1,1,1],padding='SAME')+b0)
# M*28*28*32
# pool 采样 数据量减少很多M*28*28*32 => M*7*7*32
layer1_pool = tf.nn.max_pool(layer1,ksize=[1,4,4,1],strides=[1,4,4,1],padding='SAME')
# [1 2 3 4]->[4]
# 7 layer2 out : 激励函数+乘加运算： softmax（激励函数 + 乘加运算）
# [7*7*32,1024]
w1 = tf.Variable(tf.truncated_normal([7*7*32,1024],stddev=0.1))
b1 = tf.Variable(tf.constant(0.1,shape=[1024]))
h_reshape = tf.reshape(layer1_pool,[-1,7*7*32])# M*7*7*32 -> N*N1
# [N*7*7*32] [7*7*32,1024] = N*1024
h1 = tf.nn.relu(tf.matmul(h_reshape,w1)+b1)
# 7.1 softMax
w2 = tf.Variable(tf.truncated_normal([1024,10],stddev=0.1))
b2 = tf.Variable(tf.constant(0.1,shape=[10]))
pred = tf.nn.softmax(tf.matmul(h1,w2)+b2)# N*1024 1024*10 = N*10
# N*10( 概率 )N1【0.1 0.2 0.4 0.1 0.2 。。。】
# label。 【0 0 0 0 1 0 0 0.。。】
loss0 = labeInput*tf.log(pred)
loss1 = 0
# 7.2
for m in range(0,500):# test 100
for n in range(0,10):
loss1 = loss1 - loss0[m,n]
loss = loss1/500
# 8 train
train = tf.train.GradientDescentOptimizer(0.01).minimize(loss)
# 9 run
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(100):
images,labels = mnist.train.next_batch(500)
sess.run(train,feed_dict={imageInput:images,labeInput:labels})
pred_test = sess.run(pred,feed_dict={imageInput:mnist.test.images,labeInput:labels})
acc = tf.equal(tf.arg_max(pred_test,1),tf.arg_max(mnist.test.labels,1))
acc_float = tf.reduce_mean(tf.cast(acc,tf.float32))
acc_result = sess.run(acc_float,feed_dict={imageInput:mnist.test.images,labeInput:mnist.test.labels})
print(acc_result)
刷脸识别
爬虫获取样本
import urllib
from bs4 import BeautifulSoup
html = urllib.request.urlopen(
'https://www.duitang.com/album/?id=69001447').read()
# parse url data 1 html 2 'html.parser' 3 'utf-8'
soup = BeautifulSoup(html, 'html.parser', from_encoding='utf-8')
# img
images = soup.findAll('img')
print(images)
imageName = 0
for image in images:
link = image.get('src')
print('link=', link)
fileFormat = link[-3:]
if fileFormat == 'png' or fileFormat == 'jpg':
fileSavePath = 'C:/Users/codewj/AnacondaProjects/5刷脸识别/images/' + str(imageName) + '.jpg'
imageName = imageName + 1
urllib.request.urlretrieve(link, fileSavePath)
ffmpeg
ffmpeg -i input.mp4 -r 1 -q:v 2 -f image2 pic-%03d.jpeg 视频提取帧
ffmpeg -i input.mp4 -ss 00:00:20 -t 10 -r 1 -q:v 2 -f image2 pic-%03d.jpeg ffmpeg会从input.mp4的第20s时间开始，往下10s，即20~30s这10秒钟之间，每隔1s就抓一帧，总共会抓10帧。
ffmpeg -i input.avi output.mp4 视频转格式
ffmpeg -i a.mp4 -acodec copy -vn a.aac 视频提取音频
ffmpeg -i input.mp4 -vcodec copy -an output.mp4 视频提取音频
ffmpeg -ss 00:00:15 -t 00:00:05 -i input.mp4 -vcodec copy -acodec copy output.mp4 视频剪切
ffmpeg -i input.mp4 -b:v 2000k -bufsize 2000k -maxrate 2500k output.mp4 码率控制
ffmpeg -i input.mp4 -vcodec mpeg4 output.mp4 视频编码格式转换mpeg4
ffmpeg -i input.mp4 -vf scale=960:540 output.mp4 将输入视频缩小到960x540输出
ffmpeg -i input.mp4 -i iQIYI_logo.png -filter_complex overlay output.mp4 视频添加logo
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 1 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 scale 3 5
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 数据yale 2 准备train label-》train
# 3 cnn 4 检测
import tensorflow as tf
import numpy as np
import scipy.io as sio
f = open('Yale_64x64.mat','rb')
mdict = sio.loadmat(f)
# fea gnd
train_data = mdict['fea']
train_label = mdict['gnd']
# 数据无序排列
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 [0-9] [10*N] [15*N] [0 0 1 0 0 0 0 0 0 0] -> 2
train_data = train_data.reshape(train_data.shape[0],64,64,1).astype(np.float32)/255
train_labels_new = np.zeros((165,15))# 165 image 15
for i in range(0,165):
j = int(train_label[i,0])-1 # 1-15 0-14
train_labels_new[i,j] = 1
test_data_input = test_data.reshape(test_data.shape[0],64,64,1).astype(np.float32)/255
test_labels_input = np.zeros((64,15))# 165 image 15
for i in range(0,64):
j = int(test_label[i,0])-1 # 1-15 0-14
test_labels_input[i,j] = 1
# cnn acc tf.nn tf.layer
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_labels_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_labels_input})
print('acc:%.2f',acc)