记一次 基于 卷积神经网络（CNN）的 验证码图片识别

前几天搭建好了tensorflow2的环境，今天来试验一下神奇的机器学习。

先简单编写一个java程序，收集了10000多个验证码图片，全部进行人工标注（训练素材点击下载），其中600多个用来检验预测结果。

先声明一下，验证码是从真实网站上爬取的，如下图，验证码中包含大写字母和数字，文字有旋转，背景和前景色是随机变化的，有斑点和曲线以及短划线干扰，字体看着有点像华文仿宋，大家可以根据是否对自己有用选择下载。

所有图片都已经经过人工标注，如以上验证码图片被标记为 2s6h-1586808953525-23a8680c-a80a-4deb-b1ca-a959c73a6c2f.jpg

使用以下代码进行训练，开始运行时要加载所有图片，时间有点长，大概1、2分钟，要耐心等待

# coding:utf-8import numpy as npimport tensorflow as tf#模型文件保存的路径SAVE_PATH = "E:/tensorflow/vcode-analyzer/"#验证码长宽IMAGE_WIDTH = 130IMAGE_HEIGHT = 40#验证码可能出现的字符number = ['2', '3', '4', '5', '6', '7', '8', '9']ALPHABET = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'U','V', 'W', 'X', 'Y']CHAR_SET = number + ALPHABETCHAR_SET_LEN = len(CHAR_SET)#验证码长度MAX_CAPTCHA = 4#训练批次的大小BATCH_SIZE = 128EPOCH = 4#每次训练是否将错误记录打印出来TRAIN_DEBUG = 0def text2vec(text):vector = np.zeros([MAX_CAPTCHA, CHAR_SET_LEN])try:for i, c in enumerate(text):idx = CHAR_SET.index(str(c, encoding = "utf-8").upper())vector[i][idx] = 1.0except:print("exception: " + str(text[0], encoding = "utf-8").upper()+ str(text[1], encoding = "utf-8").upper()+ str(text[2], encoding = "utf-8").upper()+ str(text[3], encoding = "utf-8").upper())return vectordef vec2text(vec):text = []for i, c in enumerate(vec):text.append(CHAR_SET[c])return "".join(text)current_index = 0train_images = []train_texts = []def load_all_train_data(image_path):global train_imagesglobal train_textsPATH = image_pathtrain_files = tf.data.Dataset.list_files(PATH+'*.jpg')def load_image(image_file, is_train):image = tf.io.read_file(image_file)image = tf.image.decode_jpeg(image)image = tf.image.rgb_to_grayscale(image)return imagetrain_iter = iter(train_files)for x in train_iter:paths = tf.strings.split(x, '\\').numpy()text = tf.strings.substr(paths[len(paths)-1], 0, 4, unit='BYTE', name=None)train_texts.append(text2vec(tf.strings.bytes_split(text).numpy()))train_images.append(load_image(x, True))return def get_next_batch(batch_size=128):global train_imagesglobal current_indexbatch_x = np.zeros([batch_size, IMAGE_HEIGHT, IMAGE_WIDTH, 1])batch_y = np.zeros([batch_size, MAX_CAPTCHA, CHAR_SET_LEN])for i in range(batch_size):if current_index >= len(train_images):current_index = current_index - len(train_images)if current_index < 0:current_index = 0batch_x[i, :] = train_images[current_index]batch_y[i, :] = train_texts[current_index]current_index = current_index + 1return batch_x, batch_ydef crack_captcha_cnn():model = tf.keras.Sequential()model.add(tf.keras.layers.Conv2D(32, (2, 2)))model.add(tf.keras.layers.PReLU())model.add(tf.keras.layers.AveragePooling2D((2, 2)))model.add(tf.keras.layers.Conv2D(64, (3, 3)))model.add(tf.keras.layers.PReLU())model.add(tf.keras.layers.MaxPool2D((2, 2)))model.add(tf.keras.layers.Conv2D(128, (5, 5)))model.add(tf.keras.layers.PReLU())model.add(tf.keras.layers.MaxPool2D((2, 2)))model.add(tf.keras.layers.Flatten())model.add(tf.keras.layers.Dense(MAX_CAPTCHA * CHAR_SET_LEN))model.add(tf.keras.layers.Reshape([MAX_CAPTCHA, CHAR_SET_LEN]))model.add(tf.keras.layers.Softmax())return modeldef train(pat):load_all_train_data(pat)try:model = tf.keras.models.load_model(SAVE_PATH + 'model')except Exception as e:print('#######Exception', e)model = crack_captcha_cnn()pile(optimizer='Adam',metrics=['accuracy'],loss='categorical_crossentropy')for times in range(500000):batch_x, batch_y = get_next_batch(BATCH_SIZE)print('times=', times, ' batch_x.shape=',batch_x.shape, ' batch_y.shape=', batch_y.shape)model.fit(batch_x, batch_y, epochs=EPOCH)if TRAIN_DEBUG == 1:v1 = np.argmax(model.predict(batch_x), axis=2)v2 = np.argmax(batch_y, axis=2)vlen = len(v1)for i in range(vlen):if (v1[i] == v2[i]).all():passelse:print("TRAIN_DEBUG: 实际 " + vec2text(v2[i]) + ", 预测 " + vec2text(v1[i]))if 0 == times % 50:print("save model at times=", times)model.save(SAVE_PATH + 'model')def predict(pat):load_all_train_data(pat)model = tf.keras.models.load_model(SAVE_PATH + 'model')success = 0count = 1000for _ in range(count):data_x, data_y = get_next_batch(1)prediction_value = model.predict(data_x)data_y = vec2text(np.argmax(data_y, axis=2)[0])prediction_value = vec2text(np.argmax(prediction_value, axis=2)[0])if data_y.upper() == prediction_value.upper():print("y预测=", prediction_value, "y实际=", data_y, "预测成功。")success += 1else:print("y预测=", prediction_value, "y实际=", data_y, "预测失败。")print("预测", count, "次", "成功率 =", success / count)passif __name__ == "__main__":#传入训练、预测图片集的路径#所有图片命名格式约定为 222s-xxxxxxxxxxxx.jpg#222s为正确验证码,xxx为任意字符train("D:\\projects\\vcode\\imgs-train\\")#train("D:\\projects\\vcode\\imgs-coded\\")predict("D:\\projects\\vcode\\imgs-coded\\")

收敛的很快，大概几百次循环loss就降到了0.1以下，accuracy持续稳定在0.9以上。

save model at times= 300times= 301 batch_x.shape= (128, 40, 130, 1) batch_y.shape= (128, 4, 31)Train on 128 samplesEpoch 1/4128/128 [==============================] - 0s 656us/sample - loss: 0.1081 - accuracy: 0.9805Epoch 2/4128/128 [==============================] - 0s 593us/sample - loss: 0.0164 - accuracy: 0.9941Epoch 3/4128/128 [==============================] - 0s 617us/sample - loss: 0.0134 - accuracy: 0.9961Epoch 4/4128/128 [==============================] - 0s 570us/sample - loss: 0.0012 - accuracy: 1.0000times= 302 batch_x.shape= (128, 40, 130, 1) batch_y.shape= (128, 4, 31)Train on 128 samples

350次训练后，切换到测试集进行预测

y预测= AX74 y实际= AX74 预测成功。y预测= UWCB y实际= UWCB 预测成功。y预测= 6YKS y实际= 6YKS 预测成功。y预测= DLUT y实际= DLUT 预测成功。y预测= RK86 y实际= RK86 预测成功。y预测= YMFV y实际= YMFV 预测成功。y预测= 9F3K y实际= 9E3K 预测失败。y预测= JY5D y实际= JY5D 预测成功。y预测= WT93 y实际= HT93 预测失败。y预测= G9NG y实际= G9NG 预测成功。预测 1000 次 成功率 = 0.76

76%的正确率，还不错！要知道，除去加载图片的时间，实际训练的时间还不到1分钟……

可以查看后一篇：发布验证码图片识别服务