主要使用Tensorflow深度学习框架和卷积神经网络(CNN)算法实现对验证码识别的功能。
步骤
1.captcha库生成验证码。
2.构造网络的输入数据和标签。
2.基于TensorFlow框架和卷积神经网络训练自己的验证码识别模型
生成验证码
使用 Python 的 captcha 库来生成即可,这个库默认是没有安装的,所以需要先安装这个库,使用 pip3 安装即可
代码如下:
import numpy as np
import tensorflow as tf
from captcha.image import ImageCaptcha#验证码生成框架
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image#图片处理标准库
import random
number = ['0','1','2','3','4','5','6','7','8','9']
alphabet = ['a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z']
ALPHABET = ['A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z']
def random_captcha_text(char_set=number+alphabet+ALPHABET ,captcha_size=4):
captcha_text=[]#list
for i in range(captcha_size ):
c=random.choice(char_set)
captcha_text .append(c)
return captcha_text
def gen_captcha_text_and_image():
image=ImageCaptcha()
captcha_text=random_captcha_text()
captcha_text="".join(captcha_text )#把list中的所有元素放入一个字符串
captcha=image.generate(captcha_text )
captcha_image=Image.open(captcha)
captcha_image=np.array(captcha_image)#将图片保存为矩阵
return captcha_text,captcha_image
if __name__ == '__main__':
text, image = gen_captcha_text_and_image()
f = plt.figure()
ax = f.add_subplot(111)
ax.text(0.1, 0.9, text, ha='center', va='center', transform=ax.transAxes)
plt.imshow(image)
plt.show()
结果如下:
构造网络的输入数据和标签
这里将这个问题看做是分类问题,验证码中一共有四个数字(或者字母),则共有(10+26+26)4=624 种可能的情况。这里为了方便进行验证,仅仅构造了数字的验证码,则每个数字有10种可能性,共有10*4中可能的情况。
涉及到的主要代码为:
def convert2gray(img):#将图像转化为灰度图
if len(img.shape) > 2:
gray = np.mean(img, -1)
# 上面的转法较快,正规转法如下
# r, g, b = img[:,:,0], img[:,:,1], img[:,:,2]
# gray = 0.2989 * r + 0.5870 * g + 0.1140 * b
return gray
else:
return img
#下面的 text2vec() 方法就是将真实文本转化为 One-Hot 编码,vec2text() 方法就是将 One-Hot 编码转回真实文本
def text2vec(text):
text_len = len(text)
if text_len > MAX_CAPTCHA:
raise ValueError('验证码最长4个字符')
vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)
for i, c in enumerate(text):
idx = i * CHAR_SET_LEN + int(c)
vector[idx] = 1
return vector
# 向量转回文本
def vec2text(vec):
text = []
char_pos = vec.nonzero()[0]#nonzero(a)返回数组a中值不为零的元素的下标
for i, c in enumerate(char_pos):
number = i % 10
text.append(str(number))
return "".join(text)
构造CNN模型
这里仅仅构造了三层卷积,每层卷积后跟池化层,一个全连接层+一个结果输出层。
# 定义CNN
def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):
x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])#为了满足TensorFlow的要求
# w_c1_alpha = np.sqrt(2.0/(IMAGE_HEIGHT*IMAGE_WIDTH)) #
# w_c2_alpha = np.sqrt(2.0/(3*3*32))
# w_c3_alpha = np.sqrt(2.0/(3*3*64))
# w_d1_alpha = np.sqrt(2.0/(8*32*64))
# out_alpha = np.sqrt(2.0/1024)
# 3 conv layer
#3个卷积+池化
w_c1 = tf.Variable(w_alpha * tf.random_normal([3, 3, 1, 32]))
b_c1 = tf.Variable(b_alpha * tf.random_normal([32]))
conv1 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x, w_c1, strides=[1, 1, 1, 1], padding='SAME'), b_c1))
conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
conv1 = tf.nn.dropout(conv1, keep_prob)
w_c2 = tf.Variable(w_alpha * tf.random_normal([3, 3, 32, 64]))
b_c2 = tf.Variable(b_alpha * tf.random_normal([64]))
conv2 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv1, w_c2, strides=[1, 1, 1, 1], padding='SAME'), b_c2))
conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
conv2 = tf.nn.dropout(conv2, keep_prob)
w_c3 = tf.Variable(w_alpha * tf.random_normal([3, 3, 64, 64]))
b_c3 = tf.Variable(b_alpha * tf.random_normal([64]))
conv3 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv2, w_c3, strides=[1, 1, 1, 1], padding='SAME'), b_c3))
conv3 = tf.nn.max_pool(conv3, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
conv3 = tf.nn.dropout(conv3, keep_prob)
# Fully connected layer
w_d = tf.Variable(w_alpha * tf.random_normal([8 * 20 * 64, 1024]))
b_d = tf.Variable(b_alpha * tf.random_normal([1024]))
dense = tf.reshape(conv3, [-1, w_d.get_shape().as_list()[0]])
dense = tf.nn.relu(tf.add(tf.matmul(dense, w_d), b_d))
dense = tf.nn.dropout(dense, keep_prob)
w_out = tf.Variable(w_alpha * tf.random_normal([1024, MAX_CAPTCHA * CHAR_SET_LEN]))
b_out = tf.Variable(b_alpha * tf.random_normal([MAX_CAPTCHA * CHAR_SET_LEN]))
out = tf.add(tf.matmul(dense, w_out), b_out)
return out
补充padding='SAME'和padding='VALID'的区别。
tensorflow 中的padding方式有“SAME”和“VALID”
这两个方式计算特征图的输出大小方式不一样。
- valid: 周围不填0进行卷积运算,无法计算的部分(矩阵的右边和下面)直接舍去。
如果padding的方法为“VALID” ,那么输出特征图的长和宽为:
new_width=new_height=⌈ W-F+1 / S⌉ - same: 周围填0进行卷积运算,0在矩阵的左右和上下均匀添加,非均匀时多的加在右边和下面。
如果padding的方法为“SAME” ,那么输出特征图的长和宽为:
new_width=new_height=⌈ W / S⌉
W为输入的size,F为filter为size,S为步长,⌈ ⌉为向上取整符号
定义一次训练的batch,定义损失函数,训练优化模型
# 生成一个训练batch
def get_next_batch(batch_size=128):
batch_x = np.zeros([batch_size, IMAGE_HEIGHT * IMAGE_WIDTH])
batch_y = np.zeros([batch_size, MAX_CAPTCHA * CHAR_SET_LEN])
# 有时生成图像大小不是(60, 160, 3)
def wrap_gen_captcha_text_and_image():
while True:
text, image = gen_captcha_text_and_image()
if image.shape == (60, 160, 3):
return text, image
for i in range(batch_size):
text, image = wrap_gen_captcha_text_and_image()
image = convert2gray(image)
batch_x[i, :] = image.flatten() / 255 # (image.flatten()-128)/128 mean为0。即值为从0到1之间
batch_y[i, :] = text2vec(text)
return batch_x, batch_y
#定义损失函数,进行模型迭代优化
def train_crack_captcha_cnn():
output = crack_captcha_cnn()
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN])
max_idx_p = tf.argmax(predict, 2)
max_idx_l = tf.argmax(tf.reshape(Y, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
correct_pred = tf.equal(max_idx_p, max_idx_l)
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 0
while True:
batch_x, batch_y = get_next_batch(64)#数据需要一个batch一个batch进行传入
_, loss_ = sess.run([optimizer, loss], feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.75})
#print(step, loss_)
# 每10 step计算一次准确率
if step % 10 == 0:
batch_x_test, batch_y_test = get_next_batch(100)
acc = sess.run(accuracy, feed_dict={X: batch_x_test, Y: batch_y_test, keep_prob: 1.})
print("Step: ",step,"准确率:" ,acc)
# 如果准确率大于50%,保存模型,完成训练
if acc > 0.60:
saver.save(sess, "./model/crack_capcha.model", global_step=step)
break
step += 1