通过摄像头捕获图像用tensorflow做手写数字识别

花了一晚上搞好了摄像头捕获图像做手写数字识别，代码基于tensorflow的mnist代码实现，作为学习tensorflow的一个过程。

先在mnist数据集上训练好网络，并保存模型。

import numpy as npimport tensorflow as tf import tensorflow.examples.tutorials.mnist.input_data as input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True) x_input = tf.placeholder(tf.float32, [None, 784])  y_actual = tf.placeholder(tf.float32, shape=[None, 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(x):    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')#input -> conv -> pool -> conv -> pool -> fc -> dropout -> softmaxdef network(x)    x_image = tf.reshape(x, [-1,28,28,1]) #-1 means arbitrary    W_conv1 = weight_variable([5, 5, 1, 32])    b_conv1 = bias_variable([32])    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)      #conv1    h_pool1 = max_pool(h_conv1)                                   #max_pool1    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)      #conv2    h_pool2 = max_pool(h_conv2)                                   #max_pool2    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)    #fc1    keep_prob = tf.placeholder("float")    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)                  #dropout    W_fc2 = weight_variable([1024, 10])    b_fc2 = bias_variable([10])    y_predicts=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) #fc2 outputreturn y_predictsy_predict=network(x_input)#see http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.htmlcross_entropy = -tf.reduce_sum(y_actual*tf.log(y_predict))train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)correct_prediction = tf.equal(tf.argmax(y_predict,1), tf.argmax(y_actual,1))    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) saver = tf.train.Saver()sess=tf.InteractiveSession()                          sess.run(tf.initialize_all_variables())for i in range(20000):  #iteration 20000 steps = (epochs * train_size) / batch_size ,epochs=21  batch = mnist.train.next_batch(64) #batch_size=64  if i%100 == 0:    train_acc = accuracy.eval(feed_dict={x_input:batch[0], y_actual: batch[1], keep_prob: 1.0})    print('step',i,'training accuracy',train_acc)    train_step.run(feed_dict={x_input: batch[0], y_actual: batch[1], keep_prob: 0.5})saver.save(sess, "model_save.ckpt") #save model#test accuracy in mnist.test datasettest_acc=accuracy.eval(feed_dict={x_input: mnist.test.images, y_actual: mnist.test.labels, keep_prob: 1.0})print("test accuracy",test_acc)

预测时使用opencv来打开摄像头捕获图像，设置ROI区域，将ROI区域图像输入加载好参数的cnn网络来识别

import numpy as npimport tensorflow as tfimport cv2def 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(x):    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')def network(x)    x_image = tf.reshape(x, [-1,28,28,1]) #-1 means arbitrary    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)  #conv1    h_pool1 = max_pool(h_conv1)                               #max_pool1    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)  #conv2    h_pool2 = max_pool(h_conv2)                               #max_pool2    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) #fc1        h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)               #dropout    y_predict=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) #fc2 outputreturn y_predictkeep_prob = tf.placeholder("float")W_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])W_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])W_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([1024])W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])sess=tf.InteractiveSession()saver = tf.train.Saver()saver.restore(sess, "./model_save.ckpt") #load model file must have ./ with tensorflow1.0cap = cv2.VideoCapture(1)while(1):    ret, frame = cap.read()    cv2.rectangle(frame,(270,200),(340,270),(0,0,255),2)    cv2.imshow("capture", frame)    roiImg = frame[200:270,270:340]    img = cv2.resize(roiImg,(28,28))    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)    np_img = img.astype(np.float32)    netoutput = network(np_img)    predictions = sess.run(netoutput,feed_dict={keep_prob: 0.5})    predicts=predictions.tolist() #tensorflow output is numpy.ndarray like [[0 0 0 0]]    label=predicts[0]    result=label.index(max(label))    print('result num:')    print(result)    if cv2.waitKey(1) & 0xFF == ord('q'):        breakcap.release()cv2.destroyAllWindows()

测试图片

随便找几个数字测试，识别还挺准的。