验证码识别方法

传统的机器学习方法，对于多位字符验证码都是采用的化整为零的方法：先分割成最小单位，再分别识别，然后再统一。
卷积神经网络方法，直接采用端到端不分割的方法：输入整张图片，输出整个图片的标记结果，具有更强的通用性。端到端的识别方法显然更具备优势，因为目前的字符型验证码为了防止被识别，多位字符已经完全融合粘贴在一起了，利用传统的技术基本很难实现分割了。

卷积神经网络方法步骤

generate_captcha.py - 利用 Captcha 库生成验证码；
captcha_model.py - CNN 模型；
train_captcha.py - 训练 CNN 模型；
predict_captcha.py - 识别验证码。

1 generate_captcha.py

图片验证码是由数字、大写字母、小写字母组成（当然你也可以根据自己的需求调整，比如添加一些特殊字符），长度为 4，所以总共有 $62^4$ 种组合验证码。

pip install captcha

#!/usr/bin/python
# -*- coding: utf-8 -*

from captcha.image import ImageCaptcha
from PIL import Image
import numpy as np
import random
import string

class generateCaptcha():
    def __init__(self,
                 width = 160,#验证码图片的宽
                 height = 60,#验证码图片的高
                 char_num = 4,#验证码字符个数
                 characters = string.digits + string.ascii_uppercase + string.ascii_lowercase):#验证码组成，数字+大写字母+小写字母
        self.width = width
        self.height = height
        self.char_num = char_num
        self.characters = characters
        self.classes = len(characters)

    def gen_captcha(self,batch_size = 50):
        X = np.zeros([batch_size,self.height,self.width,1])
        img = np.zeros((self.height,self.width),dtype=np.uint8)
        Y = np.zeros([batch_size,self.char_num,self.classes])
        image = ImageCaptcha(width = self.width,height = self.height)
		
		# 这个总体的无限循环是一个训练集的生成器，执行此代码后，会在最后的yield语句返回训练集X和Y，
		# 然后循环结束。下次再想生成验证码训练集时，会从yield语句（最后一句）开始，回到开头再执行一次循环。
        while True:
            for i in range(batch_size):
            	# 生成一个验证码字符串的随机变量，self.characters为62位的字符串（0~9A~Za~z），self.char_num=4（生成4个字符）。
                captcha_str = ''.join(random.sample(self.characters,self.char_num))

				# 使用的是ImageCaptcha类的内置方法，将字符串变为图片。convert(‘L’)：表示生成的是灰度图片，就是通道数为1的黑白图片。
                img = image.generate_image(captcha_str).convert('L')
                
                # Returns the contents of this image as a sequence object containing pixel values. The sequence object is flattened, so that values for line one follow directly after the values of line zero, and so on.
                # 将此图像的内容作为包含像素值的序列对象返回。Sequence对象是新的，因此第一行的值直接跟随在零行的值之后，依此类推。
                img = np.array(img.getdata())
                
                # 每个像素值都要除以255，这是为了归一化处理，因为灰度的范围是0~255，这里除以255就让每个像素的值在0~1之间，目的是为了加快收敛速度。
                X[i] = np.reshape(img,[self.height,self.width,1])/255.0

				# 用以生成对应的测试集Y，j和ch用以遍历刚刚生成的随机字符串，j记录index（0~3，表示第几个字符），ch记录字符串中的字符。找到Y的第i条数据中的第j个字符，然后把62长度的向量和ch相关的那个置为1。
                for j,ch in enumerate(captcha_str):
                    Y[i,j,self.characters.find(ch)] = 1
            Y = np.reshape(Y,(batch_size,self.char_num*self.classes))
            yield X,Y

    def decode_captcha(self,y):
        y = np.reshape(y,(len(y),self.char_num,self.classes))
        return ''.join(self.characters[x] for x in np.argmax(y,axis = 2)[0,:])

    def get_parameter(self):
        return self.width,self.height,self.char_num,self.characters,self.classes

    def gen_test_captcha(self):
        image = ImageCaptcha(width = self.width,height = self.height)
        captcha_str = ''.join(random.sample(self.characters,self.char_num))
        img = image.generate_image(captcha_str)
        img.save(captcha_str + '.jpg')
        
        X = np.zeros([1,self.height,self.width,1])
        Y = np.zeros([1,self.char_num,self.classes])
        img = img.convert('L')
        img = np.array(img.getdata())
        X[0] = np.reshape(img,[self.height,self.width,1])/255.0
        for j,ch in enumerate(captcha_str):
            Y[0,j,self.characters.find(ch)] = 1
        Y = np.reshape(Y,(1,self.char_num*self.classes))
        return X,Y

random.sample() method return a k length list of unique elements chosen from the population sequence or set, used for random sampling without replacement.
从序列（sequence）中随机选择k个元素，返回的是一个新的list，原来的序列不受影响。

X：一个 mini-batch 的训练数据，其 shape 为 [ batch_size, height, width, 1 ]，batch_size 表示每批次多少个训练数据，height ,width 表示验证码图片的高和宽，1 表示这是1个通道的黑白图片。

Y：X 中每个训练数据属于哪一类验证码，其形状为 [ batch_size, class ] ，对验证码中每个字符进行 One-Hot 编码，所以 class 大小为 4*62。

1.2 进入cmd

cd D:\LearningFiles\VerificationCode-yueying\sdxx_train_over
python3

from generate_captcha import generateCaptcha
g = generateCaptcha()
X,Y = g.gen_test_captcha()

2 captcha_model.py

CNN 模型
总共 5 层网络，前 3 层为卷积层，第 4、5 层为全连接层。对 4 层隐藏层都进行 dropout。
网络结构如下所示： input——>conv——>pool——>dropout——>conv——>pool——>dropout——>conv——>pool——>dropout——>fully connected layer——>dropout——>fully connected layer——>output
在这里插入图片描述

# -*- coding: utf-8 -*
import tensorflow as tf
import math

class captchaModel():
    def __init__(self,
                 width = 160,
                 height = 60,
                 char_num = 4,
                 classes = 62):
        self.width = width
        self.height = height
        self.char_num = char_num
        self.classes = classes

    def conv2d(self,x, W):
        return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

    def max_pool_2x2(self,x):
        return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                              strides=[1, 2, 2, 1], padding='SAME')

    def weight_variable(self,shape):
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)

    def bias_variable(self,shape):
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)

    def create_model(self,x_images,keep_prob):
        #first layer
        w_conv1 = self.weight_variable([5, 5, 1, 32])
        b_conv1 = self.bias_variable([32])
        h_conv1 = tf.nn.relu(tf.nn.bias_add(self.conv2d(x_images, w_conv1), b_conv1))
        h_pool1 = self.max_pool_2x2(h_conv1)
        h_dropout1 = tf.nn.dropout(h_pool1,keep_prob)
        conv_width = math.ceil(self.width/2)
        conv_height = math.ceil(self.height/2)

        #second layer
        w_conv2 = self.weight_variable([5, 5, 32, 64])
        b_conv2 = self.bias_variable([64])
        h_conv2 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout1, w_conv2), b_conv2))
        h_pool2 = self.max_pool_2x2(h_conv2)
        h_dropout2 = tf.nn.dropout(h_pool2,keep_prob)
        conv_width = math.ceil(conv_width/2)
        conv_height = math.ceil(conv_height/2)

        #third layer
        w_conv3 = self.weight_variable([5, 5, 64, 64])
        b_conv3 = self.bias_variable([64])
        h_conv3 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout2, w_conv3), b_conv3))
        h_pool3 = self.max_pool_2x2(h_conv3)
        h_dropout3 = tf.nn.dropout(h_pool3,keep_prob)
        conv_width = math.ceil(conv_width/2)
        conv_height = math.ceil(conv_height/2)

        #first fully layer
        conv_width = int(conv_width)
        conv_height = int(conv_height)
        w_fc1 = self.weight_variable([64*conv_width*conv_height,1024])
        b_fc1 = self.bias_variable([1024])
        h_dropout3_flat = tf.reshape(h_dropout3,[-1,64*conv_width*conv_height])
        h_fc1 = tf.nn.relu(tf.nn.bias_add(tf.matmul(h_dropout3_flat, w_fc1), b_fc1))
        h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

        #second fully layer
        w_fc2 = self.weight_variable([1024,self.char_num*self.classes])
        b_fc2 = self.bias_variable([self.char_num*self.classes])
        y_conv = tf.add(tf.matmul(h_fc1_drop, w_fc2), b_fc2)

        return y_conv

3 train_captcha.py

训练 CNN 模型，每批次采用 64 个训练样本，每 100 次循环检查1次识别准确度，当精准度大于0.99时，训练结束，采用 GPU 需要 4-5 个小时左右，CPU 大概需要 20 个小时左右。

#-*- coding:utf-8 -*-
import tensorflow as tf
import numpy as np
import string
import generate_captcha
import captcha_model

if __name__ == '__main__':
    captcha = generate_captcha.generateCaptcha()
    width,height,char_num,characters,classes = captcha.get_parameter()

    x = tf.placeholder(tf.float32, [None, height,width,1])
    y_ = tf.placeholder(tf.float32, [None, char_num*classes])
    keep_prob = tf.placeholder(tf.float32)

    model = captcha_model.captchaModel(width,height,char_num,classes)
    y_conv = model.create_model(x,keep_prob)
    cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y_,logits=y_conv))
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

    predict = tf.reshape(y_conv, [-1,char_num, classes])
    real = tf.reshape(y_,[-1,char_num, classes])
    correct_prediction = tf.equal(tf.argmax(predict,2), tf.argmax(real,2))
    correct_prediction = tf.cast(correct_prediction, tf.float32)
    accuracy = tf.reduce_mean(correct_prediction)

    saver = tf.train.Saver()
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        step = 1
        while True:
            batch_x,batch_y = next(captcha.gen_captcha(64))
            _,loss = sess.run([train_step,cross_entropy],feed_dict={x: batch_x, y_: batch_y, keep_prob: 0.75})
            print ('step:%d,loss:%f' % (step,loss))
            if step % 100 == 0:
                batch_x_test,batch_y_test = next(captcha.gen_captcha(100))
                acc = sess.run(accuracy, feed_dict={x: batch_x_test, y_: batch_y_test, keep_prob: 1.})
                print ('###############################################step:%d,accuracy:%f' % (step,acc))
                if acc > 0.99:
                    saver.save(sess,"./capcha_model.ckpt")
                    break
            step += 1

然后执行:

python3 train_captcha.py

在这里插入图片描述
step为步长，每100批测试一次训练集，loss为损失值，我的电脑惠普envy，i5-8250U，MX150大概需要18h完成训练。

4 predict_captcha.py

测试识别验证码

#-*- coding:utf-8 -*-
from PIL import Image, ImageFilter
import tensorflow as tf
import numpy as np
import string
import sys
import generate_captcha
import captcha_model

if __name__ == '__main__':
    captcha = generate_captcha.generateCaptcha()
    width,height,char_num,characters,classes = captcha.get_parameter()

    gray_image = Image.open(sys.argv[1]).convert('L')
    img = np.array(gray_image.getdata())
    test_x = np.reshape(img,[height,width,1])/255.0
    x = tf.placeholder(tf.float32, [None, height,width,1])
    keep_prob = tf.placeholder(tf.float32)

    model = captcha_model.captchaModel(width,height,char_num,classes)
    y_conv = model.create_model(x,keep_prob)
    predict = tf.argmax(tf.reshape(y_conv, [-1,char_num, classes]),2)
    init_op = tf.global_variables_initializer()
    saver = tf.train.Saver()
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
    with tf.Session(config=tf.ConfigProto(log_device_placement=False,gpu_options=gpu_options)) as sess:
        sess.run(init_op)
        saver.restore(sess, "capcha_model.ckpt")
        pre_list =  sess.run(predict,feed_dict={x: [test_x], keep_prob: 1})
        for i in pre_list:
            s = ''
            for j in i:
                s += characters[j]
            print(s)

然后执行:

python3 predict_captcha.py captcha/ehm5.jpg

在这里插入图片描述

PIL 图像处理

传统机器学习方法：ladingwu/identfying_code_recognize

1. 基于TensorFlow的CAPTCHA注册码识别实验
 2. github:tengxing/tensorflow-learn/captcha
3. github:Yuwailaifeng/VerificationCode_CNN
4. 基于TensorFlow识别Captcha库验证码图文教程
5. 深度学习基于TF破解验证码

python2能装tensorflow，不过需要是Linux系统或者Mac系统。
windows只能是python3.5版本安装TensorFlow。

下面是各平台安装TensorFlow的方法。
https://tensorflow.google.cn/install/

参考我的另一篇博文：
ubuntu 安装 tensorflow python2

tensorflow 验证码识别（captcha）