TensorFlow实战——验证码识别
本次验证码识别项目是基于TensorFlow和captcha库，通过卷积神经网络训练来实现的一个简单的验证码识别。由于本人设备条件有限，本次实验只针对数字验证码进行识别，有条件的同学可以对代码进行简单修改加入大小写英文字母的识别。
文章目录
- 验证码生成
- 安装captcha库
- 生成验证码
- 验证码识别
- 构造输入数据和标签
- 构造卷积网络
- 模型训练和测试`
- 全部代码
- 项目链接
验证码生成
安装captcha库
首先打开Anaconda Prompt进入到自己配置的TensorFlow环境中，然后输入pip install captcha回车即可安装capthca库，由于本人已经安装过所以显示会不一样。
生成验证码
安装好后captcha库后先测试一下生成验证码
首先导入所需的库和生成验证码的数据集，然后定义构造验证码和生成验证码的函数；生成的验证码是在number、alphabet、ALPHABET中随机抽选出来的。
import tensorflow as tf
from captcha.image import ImageCaptcha
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
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']
# 数字+大小写英文字母
# def random_captcha_text(char_set=number+alphabet+ALPHABET, captcha_size=4):
def random_captcha_text(char_set=number, captcha_size=4):
# 构造captcha_text(lsit类型) 然后循环4次从char_set中选4个元素放进captcha_text
captcha_text = []
for i in range(captcha_size):
c = random.choice(char_set)
captcha_text.append(c)
return captcha_text
def gen_captcha_text_and_image():
# 定义captcha库中的ImageCaptcha()类
image = ImageCaptcha()
# 调用random_captcha_text函数，生成长度为4的验证码
captcha_text = random_captcha_text()
# 将lsit转换成字符串
captcha_text = ''.join(captcha_text)
# 生成验证码图像
captcha = image.generate(captcha_text)
# 将验证码图像保存为np.array格式（TensorFlow网络可接受的格式）
captcha_image = Image.open(captcha)
captcha_image = np.array(captcha_image)
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()
代码运行结果：
验证码识别
构造输入数据和标签
# 将彩色图像转化为灰色图像
def convert2gray(img):
if len(img.shape) > 2:
gray = np.mean(img, -1)
return gray
else:
return img
# 文本转向量
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)
for i, c in enumerate(text):
idx = i * CHAR_SET_LEN + int(c)
vector[idx] = 1
return vector
# 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 # 让值在0~1之间
batch_y[i, :] = text2vec(text)
return batch_x, batch_y
构造卷积网络
def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):
x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
# 卷积层1
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)
# 卷积层2
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)
# 卷积层3
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)
# 全连接层
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
模型训练和测试`
def train_crack_captcha_cnn():
output = crack_captcha_cnn()
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=Y, logits=output))
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})
# 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 %d, training accuracy %g" % (step, acc))
# 如果准确率大于80%,保存模型,完成训练
if acc > 0.80:
saver.save(sess, "./model/crack_capcha.model", global_step=step)
break
step += 1
def crack_captcha(captcha_image):
output = crack_captcha_cnn()
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, "./model/crack_capcha.model-2900")
predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
text_list = sess.run(predict, feed_dict={X: [captcha_image], keep_prob: 1})
text = text_list[0].tolist()
return text
if __name__ == '__main__':
# train = 0时训练模型， train = 1时测试模型。
# 训练模块
train = 0
if train == 0:
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']
text, image = gen_captcha_text_and_image()
print("验证码图像channel:", image.shape) # (60, 160, 3)
# 图像大小
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
MAX_CAPTCHA = len(text) # 验证码长度为4
print("验证码文本最长字符数", MAX_CAPTCHA)
char_set = number
CHAR_SET_LEN = len(char_set) # 数字集长度为10
X = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT * IMAGE_WIDTH]) # 60*160
Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHA * CHAR_SET_LEN]) # 4*10
keep_prob = tf.placeholder(tf.float32) # dropout
train_crack_captcha_cnn()
# 测试模块
if train == 1:
number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
char_set = number
CHAR_SET_LEN = len(char_set)
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()
MAX_CAPTCHA = len(text)
image = convert2gray(image)
image = image.flatten() / 255
X = 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
predict_text = crack_captcha(image)
print("正确: {} 预测: {}".format(text, predict_text))
由于设备条件有限，准确率设置为80%时保存模型，CPU环境下大概一个小时完成训练。
训练结果：
测试结果：
由下图可以看出，80%准确率的模型大部分的数字还是可以识别出来的，但还是会出现个别数字识别错误。
全部代码
Captcha Generate.py
import tensorflow as tf
from captcha.image import ImageCaptcha
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
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):
# 构造captcha_text lsit 然后循环4次从char_set中选4个元素放进captcha_text
captcha_text = []
for i in range(captcha_size):
c = random.choice(char_set)
captcha_text.append(c)
return captcha_text
def gen_captcha_text_and_image():
# 定义captcha库中的ImageCaptcha()类
image = ImageCaptcha()
# 将lsit转换成字符串
captcha_text = random_captcha_text()
captcha_text = ''.join(captcha_text)
# 生成图像验证码
captcha = image.generate(captcha_text)
# 将验证码图保存为np.array格式
captcha_image = Image.open(captcha)
captcha_image = np.array(captcha_image)
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()
Captcha Recognition.py
import numpy as np
import tensorflow as tf
from captcha.image import ImageCaptcha
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
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, captcha_size=4):
# 构造captcha_text(lsit类型) 然后循环4次从char_set中选4个元素放进captcha_text
captcha_text = []
for i in range(captcha_size):
c = random.choice(char_set)
captcha_text.append(c)
return captcha_text
def gen_captcha_text_and_image():
# 定义captcha库中的ImageCaptcha()类
image = ImageCaptcha()
# 调用random_captcha_text函数，生成长度为4的验证码
captcha_text = random_captcha_text()
# 将lsit转换成字符串
captcha_text = ''.join(captcha_text)
# 生成验证码图像
captcha = image.generate(captcha_text)
# 将验证码图像保存为np.array格式（TensorFlow网络可接受的格式）
captcha_image = Image.open(captcha)
captcha_image = np.array(captcha_image)
return captcha_text, captcha_image
# 将彩色图像转化为灰色图像
def convert2gray(img):
if len(img.shape) > 2:
gray = np.mean(img, -1)
return gray
else:
return img
# 文本转向量
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)
for i, c in enumerate(text):
idx = i * CHAR_SET_LEN + int(c)
vector[idx] = 1
return vector
# 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 # 让值在0~1之间
batch_y[i, :] = text2vec(text)
return batch_x, batch_y
# 定义卷积神经网络
def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):
x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
# 卷积层1
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)
# 卷积层2
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)
# 卷积层3
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)
# 全连接层
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
# 训练
def train_crack_captcha_cnn():
output = crack_captcha_cnn()
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=Y, logits=output))
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})
# 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 %d, training accuracy %g" % (step, acc))
# 如果准确率大于80%,保存模型,完成训练
if acc > 0.80:
saver.save(sess, "./model/crack_capcha.model", global_step=step)
break
step += 1
def crack_captcha(captcha_image):
output = crack_captcha_cnn()
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, "./model/crack_capcha.model-2900")
predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
text_list = sess.run(predict, feed_dict={X: [captcha_image], keep_prob: 1})
text = text_list[0].tolist()
return text
if __name__ == '__main__':
train = 1
if train == 0:
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']
text, image = gen_captcha_text_and_image()
print("验证码图像channel:", image.shape) # (60, 160, 3)
# 图像大小
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
MAX_CAPTCHA = len(text) # 验证码长度为4
print("验证码文本最长字符数", MAX_CAPTCHA)
char_set = number
CHAR_SET_LEN = len(char_set) # 数字集长度为10
X = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT * IMAGE_WIDTH]) # 60*160
Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHA * CHAR_SET_LEN]) # 4*10
keep_prob = tf.placeholder(tf.float32) # dropout
train_crack_captcha_cnn()
if train == 1:
number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
char_set = number
CHAR_SET_LEN = len(char_set)
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()
MAX_CAPTCHA = len(text)
image = convert2gray(image)
image = image.flatten() / 255
X = 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
predict_text = crack_captcha(image)
print("正确: {} 预测: {}".format(text, predict_text))
项目链接
GitHub地址：https://github.com/WellTung666/Captcha-Recognition