captchaCnn为改良过后的验证码识别代码,推荐,此处无介绍
人工智能实验——深度学习基于TensorFlow的CAPTCHA注册码识别实验 此项目文件captcha_recognize中 gen_captcha为生成验证码部分 train_captcha为训练加测试部分 此代码中为节省实验时间,目标准确度设置为0.7 训练数据集合仅限4位数字 部分代码如下:
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 """
char_set = number + ['_'] 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):
idx = i * CHAR_SET_LEN + char2pos(c)
vector[idx] = 1
return vector
def vec2text(vec): char_pos = vec.nonzero()[0] # 显示vec中非0值的位置 text=[] for i, c in enumerate(char_pos): # enumerate(char_pos)将字符串分离成位置和字符 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 """
def get_next_batch(batch_size=128): batch_x = np.zeros([batch_size, IMAGE_HEIGHTIMAGE_WIDTH]) batch_y = np.zeros([batch_size, MAX_CAPTCHACHAR_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_HEIGHTIMAGE_WIDTH]) Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHACHAR_SET_LEN]) keep_prob = tf.placeholder(tf.float32) # dropout
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 = tf.Variable(w_alphatf.random_normal([3, 3, 1, 32])) b_c1 = tf.Variable(b_alphatf.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
def train_crack_captcha_cnn(): 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(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(step, acc)
# 如果准确率大于50%,保存模型,完成训练
if acc > 0.8:
saver.save(sess, "./crack_capcha.model", global_step=step)
break
step += 1
#训练 train_crack_captcha_cnn() #验证 def crack_captcha(captcha_image): output = crack_captcha_cnn()
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('.'))
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})
print(text_list)
text = text_list[0].tolist()
print(text)
vector = np.zeros(MAX_CAPTCHA*CHAR_SET_LEN)
i = 0
for n in text:
vector[i*CHAR_SET_LEN + n] = 1
i += 1
print(vector)
return vec2text(vector)
text, image = gen_captcha_text_and_image() image = convert2gray(image) image = image.flatten() / 255 predict_text = crack_captcha(image) print("正确: {} 预测: {}".format(text, predict_text))
运行结果如下: …… 810 0.29682732 811 0.29735017 812 0.29802948 813 0.29830387 814 0.2964266 815 0.29619786 816 0.2981005 817 0.2968874 818 0.2966752 819 0.29646474 820 0.2965102 821 0.29537976 822 0.29567286 …… 1598 0.14422612 1599 0.15173554 1600 0.13768029 1600 0.81 INFO:tensorflow:Restoring parameters from ./crack_capcha.model-1600 当正确率达到0.8则退出