使用tensorflow深度学习识别验证码

除了传统的PIL包处理图片,然后用pytessert+OCR识别意外,还可以使用tessorflow训练来识别验证码。

此篇代码大部分是转载的,只改了很少地方。

代码是运行在linux环境,tessorflow没有支持windows的python 2.7。

 

gen_captcha.py代码。

#coding=utf-8
from captcha.image import ImageCaptcha  # pip install captcha
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
import random

# 验证码中的字符, 就不用汉字了

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']
'''
number=['0','1','2','3','4','5','6','7','8','9']
alphabet =[]
ALPHABET =[]
'''

# 验证码一般都无视大小写;验证码长度4个字符
def random_captcha_text(char_set=number + alphabet + ALPHABET, captcha_size=4):
    captcha_text = []
    for i in range(captcha_size):
        c = random.choice(char_set)
        captcha_text.append(c)
    return captcha_text


# 生成字符对应的验证码
def gen_captcha_text_and_image():
    while(1):
        image = ImageCaptcha()

        captcha_text = random_captcha_text()
        captcha_text = ''.join(captcha_text)

        captcha = image.generate(captcha_text)
        #image.write(captcha_text, captcha_text + '.jpg')  # 写到文件

        captcha_image = Image.open(captcha)
        #captcha_image.show()
        captcha_image = np.array(captcha_image)
        if captcha_image.shape==(60,160,3):
            break

    return captcha_text, captcha_image






if __name__ == '__main__':
    # 测试
    text, image = gen_captcha_text_and_image()
    print image
    gray = np.mean(image, -1)
    print gray

    print image.shape
    print gray.shape
    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()

 

 

train.py代码。

#coding=utf-8
from gen_captcha import gen_captcha_text_and_image
from gen_captcha import number
from gen_captcha import alphabet
from gen_captcha import ALPHABET

import numpy as np
import tensorflow as tf

"""
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)
print   "验证码文本最长字符数", MAX_CAPTCHA  # 验证码最长4字符; 我全部固定为4,可以不固定. 如果验证码长度小于4,用'_'补齐
"""
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
MAX_CAPTCHA = 4

# 把彩色图像转为灰度图像(色彩对识别验证码没有什么用)
def convert2gray(img):
    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


"""
cnn在图像大小是2的倍数时性能最高, 如果你用的图像大小不是2的倍数,可以在图像边缘补无用像素。
np.pad(image,((2,3),(2,2)), 'constant', constant_values=(255,))  # 在图像上补2行,下补3行,左补2行,右补2行
"""

# 文本转向量
char_set = number + alphabet + ALPHABET + ['_']  # 如果验证码长度小于4, '_'用来补齐
CHAR_SET_LEN = len(char_set)


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):
        #print text
        idx = i * CHAR_SET_LEN + char2pos(c)
        #print i,CHAR_SET_LEN,char2pos(c),idx
        vector[idx] = 1
    return vector

#print text2vec('1aZ_')

# 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)


"""
#向量(大小MAX_CAPTCHA*CHAR_SET_LEN)用0,1编码 每63个编码一个字符,这样顺利有,字符也有
vec = text2vec("F5Sd")
text = vec2text(vec)
print(text)  # F5Sd
vec = text2vec("SFd5")
text = vec2text(vec)
print(text)  # SFd5
"""


# 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
        batch_y[i, :] = text2vec(text)

    return batch_x, batch_y


####################################################################

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


# 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 conv layer
    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 * 32 * 40, 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


# 训练
def train_crack_captcha_cnn():
    import time
    start_time=time.time()
    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 time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),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 u'***************************************************************第%s次的准确率为%s'%(step, acc)
                # 如果准确率大于50%,保存模型,完成训练
                if acc > 0.9:                  ##我这里设了0.9,设得越大训练要花的时间越长,如果设得过于接近1,很难达到。如果使用cpu,花的时间很长,cpu占用很高电脑发烫。
                    saver.save(sess, "crack_capcha.model", global_step=step)
                    print time.time()-start_time
                    break

            step += 1


train_crack_captcha_cnn()

 

测试代码:

output = crack_captcha_cnn()
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess, tf.train.latest_checkpoint('.'))

while(1):
   

    text, image = gen_captcha_text_and_image()
    image = convert2gray(image)
    image = image.flatten() / 255





    predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
    text_list = sess.run(predict, feed_dict={X: [image], keep_prob: 1})
    predict_text = text_list[0].tolist()

    vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)
    i = 0
    for t in predict_text:
        vector[i * 63 + t] = 1
        i += 1
        # break



    print("正确: {}  预测: {}".format(text, vec2text(vector)))

 

 

如果想要快点测试代码效果,验证码的字符不要设置太多,例如0123这几个数字就可以了。

 

反对极端面向过程编程思维方式,喜欢面向对象和设计模式的解读,喜欢对比极端面向过程编程和oop编程消耗代码代码行数的区别和原因。致力于使用oop和36种设计模式写出最高可复用的框架级代码和使用最少的代码行数完成任务,致力于使用oop和设计模式来使部分代码减少90%行,使绝大部分py文件最低减少50%-80%行的写法。
posted @ 2017-05-28 19:31  北风之神0509  阅读(30479)  评论(6编辑  收藏  举报