用tensorflow 实现手写字母的识别
第一步对一张图片进行预处理
进行预处理，缩小它的大小为28*28像素，并转变为灰度图，进行二值化处理。
代码如下：
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <stdio.h>
using namespace cv;
using namespace std;
cv::Mat org, dst, img, tmp;
void on_mouse(int event, int x, int y, int flags, void *ustc)//event鼠标事件代号，x,y鼠标坐标，flags拖拽和键盘操作的代号
{
static Point pre_pt = cv::Point(-1, -1);//初始坐标
static Point cur_pt = cv::Point(-1, -1);//实时坐标
char temp[16];
if (event == CV_EVENT_LBUTTONDOWN)//左键按下，读取初始坐标，并在图像上该点处划圆
{
org.copyTo(img);//将原始图片复制到img中
sprintf(temp, "(%d,%d)", x, y);
pre_pt = Point(x, y);
putText(img, temp, pre_pt, FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0, 255), 1, 8);//在窗口上显示坐标
circle(img, pre_pt, 2, Scalar(255, 0, 0, 0), CV_FILLED, CV_AA, 0);//划圆
imshow("img", img);
}
else if (event == CV_EVENT_MOUSEMOVE && !(flags & CV_EVENT_FLAG_LBUTTON))//左键没有按下的情况下鼠标移动的处理函数
{
img.copyTo(tmp);//将img复制到临时图像tmp上，用于显示实时坐标
sprintf(temp, "(%d,%d)", x, y);
cur_pt = Point(x, y);
putText(tmp, temp, cur_pt, FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0, 255));//只是实时显示鼠标移动的坐标
imshow("img", tmp);
}
else if (event == CV_EVENT_MOUSEMOVE && (flags & CV_EVENT_FLAG_LBUTTON))//左键按下时，鼠标移动，则在图像上划矩形
{
img.copyTo(tmp);
sprintf(temp, "(%d,%d)", x, y);
cur_pt = Point(x, y);
putText(tmp, temp, cur_pt, FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0, 255));
rectangle(tmp, pre_pt, cur_pt, Scalar(0, 255, 0, 0), 1, 8, 0);//在临时图像上实时显示鼠标拖动时形成的矩形
imshow("img", tmp);
}
else if (event == CV_EVENT_LBUTTONUP)//左键松开，将在图像上划矩形
{
org.copyTo(img);
sprintf(temp, "(%d,%d)", x, y);
cur_pt = Point(x, y);
putText(img, temp, cur_pt, FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0, 255));
circle(img, pre_pt, 2, Scalar(255, 0, 0, 0), CV_FILLED, CV_AA, 0);
rectangle(img, pre_pt, cur_pt, Scalar(0, 255, 0, 0), 1, 8, 0);//根据初始点和结束点，将矩形画到img上
imshow("img", img);
img.copyTo(tmp);
//截取矩形包围的图像，并保存到dst中
int width = abs(pre_pt.x - cur_pt.x);
int height = abs(pre_pt.y - cur_pt.y);
if (width == 0 || height == 0)
{
printf("width == 0 || height == 0");
return;
}
dst = org(Rect(min(cur_pt.x, pre_pt.x), min(cur_pt.y, pre_pt.y), width, height));
cv::resize(dst, dst, Size(28, 28));
cvtColor(dst, dst, CV_BGR2GRAY);
threshold(dst, dst, 170, 255, CV_THRESH_BINARY);
imwrite("F://temp3.jpg", dst);//注意将这里改为自己的处理结果存储地址
namedWindow("dst");
imshow("dst", dst);
waitKey(0);
}
}
int main()
{
org = imread("F:\\pram\\opencv\\minist.jpg");//读取图片地址
org.copyTo(img);
org.copyTo(tmp);
namedWindow("img");//定义一个img窗口
setMouseCallback("img", on_mouse, 0);//调用回调函数
imshow("img", img);
cv::waitKey(0);
}
图片处理前：
sample图片是这样的：
图片处理后：
##下载数据集，进行预训练，保存训练模型
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
import tensorflow as tf
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.global_variables_initializer())
y = tf.matmul(x,W) + b
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
for _ in range(1000):
batch = mnist.train.next_batch(100)
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver() # defaults to saving all variables
sess.run(tf.global_variables_initializer())
for i in range(200):#接下来的这两行就是控制训练几次，我控制了五次，200/50+1
batch = mnist.train.next_batch(50)
if i%50 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
saver.save(sess,'checkpoints/model.ckpt') #保存模型参数，注意把这里改为自己的路径
#这里必须要自己创建一个目录，否则最后会找不到路径保存。
print("test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
结果如下
进行手写字母的识别
from PIL import Image, ImageFilter
import tensorflow as tf
import matplotlib.pyplot as plt
import cv2
def imageprepare():
"""
This function returns the pixel values.
The imput is a png file location.
"""
file_name='F://temp3.jpg'#导入自己的图片地址
#in terminal 'mogrify -format png *.jpg' convert jpg to png
im = Image.open(file_name).convert('L')
im.save("F://sample.jpg")
plt.imshow(im)
plt.show()
tv = list(im.getdata()) #get pixel values
#normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
tva = [ (255-x)*1.0/255.0 for x in tv]
#print(tva)
return tva
"""
This function returns the predicted integer.
The imput is the pixel values from the imageprepare() function.
"""
# Define the model (same as when creating the model file)
result=imageprepare()
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
init_op = tf.initialize_all_variables()
"""
Load the model2.ckpt file
file is stored in the same directory as this python script is started
Use the model to predict the integer. Integer is returend as list.
Based on the documentatoin at
https://www.tensorflow.org/versions/master/how_tos/variables/index.html
"""
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(init_op)
saver.restore(sess, 'checkpoints/model.ckpt')#这里使用了之前保存的模型参数
#print ("Model restored.")
prediction=tf.argmax(y_conv,1)
predint=prediction.eval(feed_dict={x: [result],keep_prob: 1.0}, session=sess)
print(h_conv2)
print('recognize result:')
print(predint[0])
在这的问题就是找不到模块，这个时候就自己去下载，激活自己的环境，activate tensorflow(我的环境的名字叫这个)，pip install 要安装的包名
CV2对应的包是：opencv-python，pil对应的是pillow，图片地址不要弄错了，其他的就还好；
结果如下：
