def gen_captcha_text_and_image(iter):
image = ImageCaptcha(width=captcha_params.get_width(),
height=captcha_params.get_height(),
font_sizes=[30])
#print(image)
#captcha_text = random_text()
captcha_text = "oO" + random_text() #proof that "o" and "O" looks the same
path = '../images/' #go up one directory then create images folder
if os.path.exists(
path) == False: # if the folder is not existed, create it
os.mkdir(path)
captcha = image.generate(captcha_text)
print('c: ', captcha)
# naming rules: num(in order)+'_'+'captcha text'.include num is for avoiding the same name
image.write(captcha_text, path + str(iter) + '_' + captcha_text + '.png')
captcha_image = Image.open(captcha)
captcha_image = np.array(captcha_image)
return captcha_text, captcha_image
import h5py from keras.models import model_from_json from keras.utils import plot_model from keras.preprocessing.image import ImageDataGenerator import matplotlib from matplotlib import pyplot as plt batch_size = 512 nb_epoch = 100 step_epoch = 7 MAX_CAPTCHA = captcha_params.get_captcha_size() CHAR_SET_LEN = captcha_params.get_char_set_len() # input image dimensions img_rows, img_cols = captcha_params.get_height(), captcha_params.get_width() # number of convolutional filters to use nb_filters1 = 32 nb_filters2 = 64 nb_filters3 = 64 # size of pooling area for max pooling pool_size = (2, 2) # convolution kernel size kernel_size = (3, 3) # the data, shuffled and split between train and test sets (X_train, Y_train), (X_test, Y_test) = load_data(tol_num=3425, train_num=3082)
# The full neural network code!
###############################
import keras
from load_data import *
import captcha_params
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
(x_train, y_train), (x_test,
y_test) = load_data(tol_num=captcha_params.TOTAL_NUM,
train_num=captcha_params.TRAIN_NUM)
# input image dimensions
img_rows, img_cols = captcha_params.get_height(), int(
captcha_params.get_width() / captcha_params.CAPTCHA_NB_LETTERS)
MAX_CAPTCHA = captcha_params.get_captcha_size()
CHAR_SET_LEN = captcha_params.get_char_set_len()
batch_size = captcha_params.BATCH_SIZE
nb_classes = MAX_CAPTCHA * CHAR_SET_LEN
nb_epoch = captcha_params.EPOCH
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
pool_size = (2, 2)
# convolution kernel size
kernel_size = (3, 3)
import os
from PIL import Image
import numpy as np
import random
import captcha_params
np.random.seed(177)
MAX_CAPTCHA = captcha_params.get_captcha_size()
CHAR_SET_LEN = captcha_params.get_char_set_len()
CHAR_SET = captcha_params.get_char_set()
Y_LEN = captcha_params.get_y_len()
height = captcha_params.get_height()
width = captcha_params.get_width()
# return the index of the max_num in the array
def get_max(array):
max_num = max(array)
for i in range(len(array)):
if array[i] == max_num:
return i
def get_text(array):
text = []
max_num = max(array)
for i in range(len(array)):
# The full neural network code!
###############################
import keras
from load_data import *
import captcha_params
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
(x_train, y_train), (x_test, y_test) = load_data(tol_num = captcha_params.TOTAL_NUM,train_num = captcha_params.TRAIN_NUM)
# input image dimensions
img_rows, img_cols = captcha_params.get_height(), int(captcha_params.get_width() / captcha_params.CAPTCHA_NB_LETTERS)
MAX_CAPTCHA = captcha_params.get_captcha_size()
CHAR_SET_LEN = captcha_params.get_char_set_len()
batch_size = captcha_params.BATCH_SIZE
nb_classes = MAX_CAPTCHA*CHAR_SET_LEN
nb_epoch = captcha_params.EPOCH
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
pool_size = (2, 2)
# convolution kernel size
kernel_size = (3, 3)
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
