使用 Keras 构建验证码识别系统（CNN + LSTM）

本教程介绍如何使用 Keras（TensorFlow）搭建一个用于识别图像验证码的深度学习模型，采用 CNN 提取图像特征，LSTM 建模字符序列，最后输出预测结果。

1. 安装依赖

pip install tensorflow pillow numpy captcha2. 生成验证码数据集

1. from captcha.image import ImageCaptcha
   import string, random, os
   from PIL import Image
   characters = string.digits + string.ascii_uppercase
   captcha_length = 4
   img_width, img_height = 160, 60
   def generate_captcha(output_dir='keras_captcha', num_samples=5000):
   os.makedirs(output_dir, exist_ok=True)
   generator = ImageCaptcha(width=img_width, height=img_height)
   for i in range(num_samples):
   text = ''.join(random.choices(characters, k=captcha_length))
   image = generator.generate_image(text)
   image.save(f"{output_dir}/{text}{i}.png")
   generate_captcha()1. 3. 构建数据加载器
   import tensorflow as tf
   import numpy as np
   char_to_idx = {c: i for i, c in enumerate(characters)}
   idx_to_char = {i: c for c, i in char_to_idx.items()}
   def parse_image(filename):
   更多内容访问ttocr.com或联系1436423940
   label_str = tf.strings.split(tf.strings.split(filename, os.sep)[-1], '')[0]
   label = tf.strings.bytes_split(label_str)
   label = tf.map_fn(lambda c: char_to_idx[c.numpy().decode()], label, fn_output_signature=tf.int32)image = tf.io.read_file(filename)
   image = tf.image.decode_png(image, channels=3)
   image = tf.image.convert_image_dtype(image, tf.float32)
   image = tf.image.resize(image, [img_height, img_width])
   return image, labeldef create_dataset(data_dir, batch_size=64):
   files = tf.data.Dataset.list_files(data_dir + '/*.png')
   dataset = files.map(lambda f: tf.py_function(parse_image, [f], [tf.float32, tf.int32]),
   num_parallel_calls=tf.data.AUTOTUNE)
   dataset = dataset.map(lambda img, label: (img, tf.reshape(label, [captcha_length])))
   return dataset.shuffle(1000).batch(batch_size).prefetch(tf.data.AUTOTUNE)
2. 构建模型
   from tensorflow.keras import layers, models
   def build_model():
   inputs = layers.Input(shape=(img_height, img_width, 3))x = layers.Conv2D(32, 3, activation='relu', padding='same')(inputs)
   x = layers.MaxPooling2D()(x)
   x = layers.Conv2D(64, 3, activation='relu', padding='same')(x)
   x = layers.MaxPooling2D()(x)
   x = layers.Conv2D(128, 3, activation='relu', padding='same')(x)
   x = layers.MaxPooling2D()(x)

x = layers.Reshape((x.shape[1], x.shape[2]*x.shape[3]))(x)
x = layers.Bidirectional(layers.LSTM(128, return_sequences=True))(x)
x = layers.Bidirectional(layers.LSTM(128))(x)

outputs = [layers.Dense(len(characters), activation='softmax', name=f'char_{i}')(x) for i in range(captcha_length)]
model = models.Model(inputs=inputs, outputs=outputs)
return modelmodel = build_model()
model.compile(
loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy']
)
5. 训练模型

train_ds = create_dataset('keras_captcha', batch_size=64)
model.fit(train_ds, epochs=10, steps_per_epoch=100)
6. 推理函数
import numpy as np
def predict_image(model, path):
img = tf.io.read_file(path)
img = tf.image.decode_png(img, channels=3)
img = tf.image.convert_image_dtype(img, tf.float32)
img = tf.image.resize(img, [img_height, img_width])
img = tf.expand_dims(img, axis=0)preds = model.predict(img)
pred_chars = [idx_to_char[np.argmax(p)] for p in preds]
return ''.join(pred_chars)print(predict_image(model, 'keras_captcha/Z9C4_12.png'))