python 识别验证码

作者: 魔童转世 | 来源:发表于2018-09-04 18:32 被阅读0次

keras 视频学习

https://morvanzhou.github.io/tutorials/machine-learning/keras/

学习此篇文章共花费了我1周的业余时间,幸好没丢人有点结果了

1、下载数据部分

自己写了一个thinkphp 生成验证码，刚开始生成的比较负责，怎么训练都不行后来写得的比较简单，这样就能快速验证自己的模型是否正确

import os
from urllib import request


for idx in range(1000):
    urlString ='http://www.code.com/public/index.php/index'
    response =  request.urlopen(urlString)
//由于thinkphp 验证码是单独的一个机制  本人也不太会php 所以就把验证码的值放在headers里面
    imageName ='../data/'+ str(idx)+'_'+response.headers['code']+'.png'

    with open(imageName,'wb') as img:
        img.write(response.read())

2、处理数据

把数据弧度处理并二值化减小计算压力

import os

from PIL import Image

pics_dir='../data'
processed_pics_dir='./data'
# 将图片灰度化以减少计算压力
def preprocess_pics():
    for (dirpath, dirnames, filenames) in os.walk(pics_dir):
        for filename in filenames:
            if filename.endswith('.png'):
                with open(pics_dir + '/' + filename, 'rb') as f:
                    image = Image.open(f)
                    # 直接使用convert方法对图片进行灰度操作
                    image = image.convert('L')
                    image = convert_Image(image)
                    with open(processed_pics_dir + '/' + filename, 'wb') as of:
                        image.save(of)

def convert_Image(img, standard=127.5):
    '''
    【灰度转换】
    '''
    image = img.convert('L')

    '''
    【二值化】
    根据阈值 standard , 将所有像素都置为 0(黑色) 或 255(白色), 便于接下来的分割
    '''
    pixels = image.load()
    for x in range(image.width):
        for y in range(image.height):
            if pixels[x, y] > standard:
                pixels[x, y] = 255
            else:
                pixels[x, y] = 0
    return image


preprocess_pics()  #会覆盖掉手动标注的数据请慎用

3、编写loadData 方法以方便神经网络调用

import os
import random

import numpy as np
from PIL import Image


IMAGE_HEIGHT=30
IMAGE_WIDTH=110

captcha_chars = '01'
# captcha_chars = '0123456789'
char_idx_mappings = {}
idx_char_mappings = {}

for idx, c in enumerate(list(captcha_chars)):
    char_idx_mappings[c] = idx
    idx_char_mappings[idx] = c

MAX_CAPTCHA = 4 #验证码长度
CHAR_SET_LEN = len(captcha_chars)
# 验证码转化为向量
def text2vec(text):
    text_len = len(text)
    if text_len > MAX_CAPTCHA:
        raise ValueError('验证码最长%d个字符'%MAX_CAPTCHA)
    vector = np.zeros(MAX_CAPTCHA*CHAR_SET_LEN)
    for i, c in enumerate(text):
        idx = i * CHAR_SET_LEN + char_idx_mappings[c]
        vector[idx] = 1
    return vector
# 向量转化为验证码
def vec2text(vec):
    text = []
    vec[vec<0.5] = 0
    char_pos = vec.nonzero()[0]
    for i, c in enumerate(char_pos):
        char_idx = c % CHAR_SET_LEN
        text.append(idx_char_mappings[char_idx])
    return ''.join(text)


# 向量转化为验证码
def vec2text1(vec):
    text = []
    for i in range(MAX_CAPTCHA):
        data = vec[i*CHAR_SET_LEN:(i+1)*CHAR_SET_LEN]
        index = data.tolist().index(max(data))
        text.append(idx_char_mappings[index])
    return ''.join(text)






# processed_pics_dir='../data'
processed_pics_dir='./data'

img_idx_filename_mappings = {}
img_idx_text_mappings = {}
img_idxes = []

index=0
# 首先遍历目录，根据文件名初始化idx->filename, idx->text的映射，同时初始化idx列表
for (dirpath, dirnames, filenames) in os.walk(processed_pics_dir):
    for filename in filenames:
        if filename.endswith('.png'):
            idx = int(filename[0:filename.index('_')])
            text = filename[int(filename.index('_')+1):int(filename.index('.'))]
            img_idx_filename_mappings[idx] = filename
            img_idx_text_mappings[idx] = text
            img_idxes.append(idx)


# 为避免频繁读入文件，将images及labels缓存起来
sample_idx_image_mappings = {}
sample_idx_label_mappings = {}
# 提供给外部取得一批训练数据的接口
def get_batch_data(batch_size):
    images = []
    labels = []
    target_idxes = random.sample(img_idxes, batch_size)
    for target_idx in target_idxes:
        image = None
        if target_idx in sample_idx_image_mappings:
            image = sample_idx_image_mappings[target_idx]
        else:
            with open(processed_pics_dir + '/' + img_idx_filename_mappings[target_idx], 'rb') as f:
                image = Image.open(f)
                image=image.convert('L')
                # 对数据正则化，tensorflow处理时更高效
                image = np.array(image)/255.0

            sample_idx_image_mappings[target_idx] = image
        label = None
        if target_idx in sample_idx_label_mappings:
            label = sample_idx_label_mappings[target_idx]
        else:
            label = text2vec(img_idx_text_mappings[target_idx])
            sample_idx_label_mappings[target_idx] = label
        images.append(image)
        labels.append(label)
    x = np.array(images)
    y = np.array(labels)
    return (x, y)

#测试部分 主要为了debug
(x,y)=get_batch_data(1)
#
print(y[0])
# print(x.reshape(-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1).shape)

4、编写神经网络部分

from pathlib import Path
from keras.models import Sequential
from keras.layers import Dense, InputLayer, Activation
from keras.layers.core import Reshape, Dropout, Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.pooling import MaxPooling2D
from keras.layers import Input, concatenate
from keras.models import Model
from keras.optimizers import Adam

import phpcode_data











model = Sequential()
model.add(InputLayer(input_shape=(phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH)))
model.add(Reshape((phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH, 1)))

# 三组卷积逻辑，每组包括两个卷积层及一个池化层

model.add(Conv2D(
    filters=32,
    kernel_size=5,
    strides=(1, 1),
    padding='same',
    use_bias=True,
    input_shape=(phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH, 1)
))
model.add(Activation('relu'))
model.add(MaxPooling2D(
    pool_size=2,
    strides=2,
    padding='same'
))


model.add(Conv2D(
    filters=64,
    kernel_size=5,
    strides=(1, 1),
    padding='same',
    use_bias=True
))
model.add(Activation('relu'))
model.add(MaxPooling2D(
    pool_size=2,
    strides=2,
    padding='same'
))

model.add(Conv2D(
    filters=128,
    kernel_size=5,
    strides=(1, 1),
    padding='same',
    use_bias=True
))
model.add(Activation('relu'))
model.add(MaxPooling2D(
    pool_size=2,
    strides=2,
    padding='same'
))




model.add(Flatten())


# 全连接层，输出维数是kaptcha_data.MAX_CAPTCHA * kaptcha_data.CHAR_SET_LEN
image_input = Input(shape=(phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH))
encoded_image = model(image_input)

encoded_softmax = []
for i in range(phpcode_data.MAX_CAPTCHA):
    out1 = Dense(128, activation="relu")(encoded_image)
    output1 = Dense(phpcode_data.CHAR_SET_LEN, activation="softmax")(out1)
    encoded_softmax.append(output1)
output = concatenate(encoded_softmax)

output1 = Dense(128,activation='relu')(output)
output2 = Dense(phpcode_data.MAX_CAPTCHA * phpcode_data.CHAR_SET_LEN,activation='softmax')(output1)

model = Model(inputs=[image_input], outputs=output2)


# model.add(Dense(1024))
# model.add(Activation('relu'))
#
# model.add(Dense(phpcode_data.MAX_CAPTCHA * phpcode_data.CHAR_SET_LEN))
# model.add(Activation('softmax'))

adam = Adam(lr=1e-4)
# 编译模型，损失函数使用categorical_crossentropy， 优化函数使用adadelta，每一次epoch度量accuracy
model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])

# 模型可视化
from keras.utils import plot_model
plot_model(model, to_file='captcha_recognition_model.png')


if Path('kaptcha_recognition.h5').is_file():
    model.load_weights('kaptcha_recognition.h5')
batch_size = 100

for epoch in range(10000):
    print("epoch {}...".format(epoch))
    (x_train, y_train) = phpcode_data.get_batch_data(batch_size)
    train_result = model.train_on_batch(x=x_train, y=y_train)
    print(' loss: %.6f, accuracy: %.6f' % (train_result[0], train_result[1]))
    if epoch % 5 == 0:
        # 保存模型的权值`
        model.save_weights('kaptcha_recognition.h5')
        # 当准确率大于0.5时，说明学习到的模型已经可以投入实际使用，停止计算

5、验证部分

from pathlib import Path

import numpy as np
from PIL import Image
from keras import Sequential, Input, Model
from keras.engine import InputLayer
from keras.layers import Flatten, Dense, Activation, Conv2D, MaxPooling2D, concatenate, Reshape
from keras.optimizers import Adam

import phpcode_data



model = Sequential()
model.add(InputLayer(input_shape=(phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH)))
model.add(Reshape((phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH, 1)))

# 三组卷积逻辑，每组包括两个卷积层及一个池化层

model.add(Conv2D(
    filters=32,
    kernel_size=5,
    strides=(1, 1),
    padding='same',
    use_bias=True,
    input_shape=(phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH, 1)
))
model.add(Activation('relu'))
model.add(MaxPooling2D(
    pool_size=2,
    strides=2,
    padding='same'
))


model.add(Conv2D(
    filters=64,
    kernel_size=5,
    strides=(1, 1),
    padding='same',
    use_bias=True
))
model.add(Activation('relu'))
model.add(MaxPooling2D(
    pool_size=2,
    strides=2,
    padding='same'
))

model.add(Conv2D(
    filters=128,
    kernel_size=5,
    strides=(1, 1),
    padding='same',
    use_bias=True
))
model.add(Activation('relu'))
model.add(MaxPooling2D(
    pool_size=2,
    strides=2,
    padding='same'
))




model.add(Flatten())


# 全连接层，输出维数是kaptcha_data.MAX_CAPTCHA * kaptcha_data.CHAR_SET_LEN
image_input = Input(shape=(phpcode_data.IMAGE_HEIGHT, phpcode_data.IMAGE_WIDTH))
encoded_image = model(image_input)

encoded_softmax = []
for i in range(phpcode_data.MAX_CAPTCHA):
    out1 = Dense(128, activation="relu")(encoded_image)
    output1 = Dense(phpcode_data.CHAR_SET_LEN, activation="softmax")(out1)
    encoded_softmax.append(output1)
output = concatenate(encoded_softmax)

output1 = Dense(128,activation='relu')(output)
output2 = Dense(phpcode_data.MAX_CAPTCHA * phpcode_data.CHAR_SET_LEN,activation='softmax')(output1)

model = Model(inputs=[image_input], outputs=output2)


adam = Adam(lr=1e-4)
# 编译模型，损失函数使用categorical_crossentropy， 优化函数使用adadelta，每一次epoch度量accuracy
model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])


if Path('kaptcha_recognition.h5').is_file():
    model.load_weights('kaptcha_recognition.h5')


def get_single_image(filename):
    images = []
    with open(filename, 'rb') as f:
        image = Image.open(f)
        image = image.convert('L')
        images.append(np.array(image)/255)
    return np.array(images)
# 计算某一张图片的验证码
predicts = model.predict(get_single_image('data/82_1010.png'), batch_size=1)

print(predicts)
print('predict: %s' % phpcode_data.vec2text1(predicts[0]))

代码放在github上了如果有人看到了我希望能加我微信咱们一起学习https://github.com/weihaigang/codeimage

python 识别验证码

1、下载数据部分

2、处理数据

3、编写loadData 方法以方便神经网络调用

4、编写神经网络部分

5、验证部分

相关文章

网友评论

延伸阅读

深度阅读

栏目导航

热点阅读

python 识别验证码

1、下载数据部分

2、处理数据

3、编写loadData 方法 以方便神经网络调用

4、编写神经网络部分

5、验证部分

相关文章

网友评论

延伸阅读

深度阅读

栏目导航

热点阅读

3、编写loadData 方法以方便神经网络调用