from tensorflow.examples.tutorials.mnist import input_data

# 保存模型需要的库

from tensorflow.python.framework.graph_util import convert_variables_to_constants

from tensorflow.python.framework import graph_util

# 导入其他库

import tensorflow as tf

import cv2

import numpy as np

# 获取MINIST数据

mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

# 创建会话

sess = tf.InteractiveSession()

# 占位符

x = tf.placeholder("float", shape=[None, 784], name="Mul")

y_ = tf.placeholder("float", shape=[None, 10], name="y_")

# 变量

W = tf.Variable(tf.zeros([784, 10]), name='x')

b = tf.Variable(tf.zeros([10]), 'y_')

# 权重

def weight_variable(shape):

initial = tf.truncated_normal(shape, stddev=0.1)

return tf.Variable(initial)

# 偏差

def bias_variable(shape):

initial = tf.constant(0.1, shape=shape)

return tf.Variable(initial)

# 卷积

def conv2d(x, W):

return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

# 最大池化

def max_pool_2x2(x):

return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],

strides=[1, 2, 2, 1], padding='SAME')

# 相关变量的创建

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])

# 激活函数

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])

W_fc2 = weight_variable([1024, 10])

b_fc2 = bias_variable([10])

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("float", name='rob')

h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 用于训练用的softmax函数

y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2, name='res')

# 用于训练作完后，作测试用的softmax函数

y_conv2 = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2, name="final_result")

# 交叉熵的计算，返回包含了损失值的Tensor。

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))

# 优化器，负责最小化交叉熵

train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

# 计算准确率

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

# 初始化所以变量

sess.run(tf.global_variables_initializer())

# 保存输入输出，可以为之后用

tf.add_to_collection('res', y_conv)

tf.add_to_collection('output', y_conv2)

tf.add_to_collection('x', x)

# 训练开始

for i in range(10000):

batch = mnist.train.next_batch(50)

if i % 100 == 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))

# run()可以看做输入相关值给到函数中的占位符，然后计算的出结果，这里将batch[0]，给xbatch[1]给y_

train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

# 将当前图设置为默认图

graph_def = tf.get_default_graph().as_graph_def()

# 将上面的变量转化成常量，保存模型为pb模型时需要,注意这里的final_result和前面的y_con2是同名，只有这样才会保存它，否则会报错，

# 如果需要保存其他tensor只需要让tensor的名字和这里保持一直即可

output_graph_def = tf.graph_util.convert_variables_to_constants(sess,graph_def, ['final_result'])

# 用saver 保存模型

saver = tf.train.Saver()

saver.save(sess, "model_data/model")

"""

基于TensorFlow的手写数字识别

Author_Zjh

2018/12/3

"""

import numpy as np

import cv2

import matplotlib.pyplot as plt

import imutils

import matplotlib.patches as mpatches

from skimage import data,segmentation,measure,morphology,color

import tensorflow as tf

class Number_recognition():

""" 模型恢复初始化"""

def __init__(self,img):

self.sess = tf.InteractiveSession()

saver = tf.train.import_meta_graph('model_data/model.meta')

saver.restore(self.sess, 'model_data/model') #模型恢复

# graph = tf.get_default_graph()

# 获取输入tensor,,获取输出tensor

self.input_x = self.sess.graph.get_tensor_by_name("Mul:0")

self.y_conv2 = self.sess.graph.get_tensor_by_name("final_result:0")

self.Preprocessing(img)#图像预处理

def recognition(self,im):

im = cv2.resize(im, (28, 28), interpolation=cv2.INTER_CUBIC)

x_img = np.reshape(im, [-1, 784])

output = self.sess.run(self.y_conv2, feed_dict={self.input_x: x_img})

print('您输入的数字是 %d' % (np.argmax(output)))

return np.argmax(output)#返回识别的结果

def Preprocessing(self,image):

if image.shape[0]>800:

image = imutils.resize(image, height=800) #如果图像太大局部阈值分割速度会稍慢些，因此图像太大时进行降采样

img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) # convert to gray picture

m1, n1 = img.shape

k = int(m1 / 19) + 1

l = int(n1 / 19) + 1

img = cv2.GaussianBlur(img, (3, 3), 0) # 高斯滤波

imm = img.copy()

# 基于Niblack的局部阈值分割法，对于提取文本类图像分割效果比较好

for x in range(k):

for y in range(l):

s = imm[19 * x:19 * (x + 1), 19 * y:19 * (y + 1)]

me = s.mean() # 均值

var = np.std(s) # 方差

t = me * (1 - 0.2 * ((125 - var) / 125))

ret, imm[19 * x:19 * (x + 1), 19 * y:19 * (y + 1)] = cv2.threshold(

imm[19 * x:19 * (x + 1), 19 * y:19 * (y + 1)], t, 255, cv2.THRESH_BINARY_INV)

label_image = measure.label(imm) # 连通区域标记

for region in measure.regionprops(label_image): # 循环得到每一个连通区域属性集

# 忽略小区域

if region.area < 100:

continue

minr, minc, maxr, maxc = region.bbox# 得到外包矩形参数

cv2.rectangle(image, (minc, minr), (maxc, maxr), (0, 255, 0), 2)#绘制连通区域

im2 = imm[minr - 5:maxr + 5, minc - 5:maxc + 5] #获得感兴趣区域，也即每个数字的区域

number = self.recognition(im2)#进行识别

cv2.putText(image, str(number), (minc, minr - 10), 0, 2, (0, 0, 255), 2)#将识别结果写在原图上

cv2.imshow("Nizi", imm)

cv2.imshow("Annie", image)

cv2.waitKey(0)

if __name__=='__main__':

img = cv2.imread("num.jpg")

x=Number_recognition(img)