基于tensorflow的验证码识别
验证码最初的设计初衷是区分人和机器，随着AI技术的发展，大部分的验证码已经无法实现这样的功能了。为了验证这一事实，决定采用tensorflow来搭建深度学习模型，以此来验证深度学习对验证码识别的准确度。
构建训练数据集
收集海量的验证码是一件困难的工作。因此，我们采用常用的验证码生成库来生成训练案例。
1 | from captcha.image import ImageCaptcha |
最终测试的验证码：
模型数据预处理
模型数据预处理，统一输入img的维度。我们这里通过转换为灰度的方式来达到统一输入维度。1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77import numpy as np
# 如果图片的维度在三维及以上，即长、宽、通道。我们通过对上个通道上的数据进行求平均来达到灰度的效果。[255, 255, 254] => 254.666
def convert2gray(img):
if len(img.shape) > 2:
gray = np.mean(img, -1)
return gray
else:
return img
# char_set包含所有数字、大小写英文字母
char_set = ic.number + ic.alphabet + ic.ALPHABET + ['_'] # 如果验证码长度小于4, '_'用来补齐
CHAR_SET_LEN = len(char_set)
# 这个方法是将4位字符转为252长度的向量
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)
def char2pos(c):
if c =='_':
k = 62
return k
k = ord(c)-48
if k > 9:
k = ord(c) - 55
if k > 35:
k = ord(c) - 61
if k > 61:
raise ValueError('No Map')
return k
for i, c in enumerate(text):
idx = i * CHAR_SET_LEN + char2pos(c)
vector[idx] = 1
return vector
# 向量转回文本
def vec2text(vec):
char_pos = vec.nonzero()[0]
text=[]
for i, c in enumerate(char_pos):
char_at_pos = i #c/63
char_idx = c % CHAR_SET_LEN
if char_idx < 10:
char_code = char_idx + ord('0')
elif char_idx <36:
char_code = char_idx - 10 + ord('A')
elif char_idx < 62:
char_code = char_idx- 36 + ord('a')
elif char_idx == 62:
char_code = ord('_')
else:
raise ValueError('error')
text.append(chr(char_code))
return "".join(text)
# 生成一个训练batch，batch长度128
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 = ic.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
batch_y[i,:] = text2vec(text)
return batch_x, batch_y
构建训练模型
采用CNN，包含三个卷积池化层和两个全链接层1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83X = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT*IMAGE_WIDTH])
Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHA*CHAR_SET_LEN])
keep_prob = tf.placeholder(tf.float32) # dropout
# 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])
#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 个卷积层
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)
#out = tf.nn.softmax(out)
return out
#开始训练及保存模型
def train_crack_captcha_cnn():
output = crack_captcha_cnn()
# loss
#loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output, Y))
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
# 最后一层用来分类的softmax和sigmoid有什么不同？
# optimizer 为了加快训练 learning_rate应该开始大，然后慢慢衰
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)
_, loss_ = sess.run([optimizer, loss], feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.75})
print(step, loss_)
# 每100 step计算一次准确率
if step % 100 == 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, acc)
# 如果准确率大于50%,保存模型,完成训练
if acc > 0.9:
saver.save(sess, "./Model/crack_capcha.model", global_step=step)
break
step += 1
经过10100次训练后，准确率达到90%以上，训练时间1小时10分钟。1
2
3
4
5
6
7
8(10096, 0.01938362)
(10097, 0.017134182)
(10098, 0.022120956)
(10099, 0.019756839)
(10100, 0.024086259)
(10100, 0.90750003)
End: 2017-11-17 10:24:31
Spend Time: 1:09:57.760766
模型加载及测试
训练完成的模型被保存，需要重新被加载。1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
def crack_captcha(captcha_image):
output = tc.crack_captcha_cnn()
saver = tf.train.Saver()
with tf.Session() as sess:
with tf.device("/cpu:0"):
saver.restore(sess, "./Model/crack_capcha.model-10100")
predict = tf.argmax(tf.reshape(output, [-1, tc.MAX_CAPTCHA, tc.CHAR_SET_LEN]), 2)
text_list = sess.run(predict, feed_dict={tc.X: [captcha_image], tc.keep_prob: 1})
text = text_list[0].tolist()
vector = np.zeros(tc.MAX_CAPTCHA*tc.CHAR_SET_LEN)
i = 0
for n in text:
vector[i*tc.CHAR_SET_LEN + n] = 1
i += 1
return tc.vec2text(vector)
text, image = ic.gen_captcha_text_and_image()
f = plt.figure()
plt.imshow(image)
plt.show()
image = tc.convert2gray(image)
image = image.flatten() / 255
predict_text = crack_captcha(image)
print("正确: {} 预测: {}".format(text, predict_text))
最终的预测结果：
1
2INFO:tensorflow:Restoring parameters from ./Model/crack_capcha.model-10100
正确: rLwX 预测: rLwX