【DL项目】基于卷积神经网络实现人脸表情识别

亦凉 2022-05-21 12:08 160阅读 0赞

*  更新时间：2018-07-05

### 前言 ###

项目是好久之前做的，现在可能类似的demo也有很多了，已知忘记发博客和上传GitHub了，刚传上去，地址：[https://github.com/roguesir/DL-ML-project/tree/master/Expression-Recognition][https_github.com_roguesir_DL-ML-project_tree_master_Expression-Recognition]

### 结构设计 ###

采用fer2013人脸表情数据集，使用裁剪和旋转变换进行数据增强，处理后的数据量达到105000张，大小为48x48的黑白图片。  
![这里写图片描述][70]  
基本结构如下：  
![这里写图片描述][70 1]

### 训练结果 ###

<table> 
 <thead> 
  <tr> 
   <th align="center">模型</th> 
   <th align="center">准确率（%）</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td align="center">model-basic</td> 
   <td align="center">90.11</td> 
  </tr> 
  <tr> 
   <td align="center">model-8</td> 
   <td align="center">99.27</td> 
  </tr> 
  <tr> 
   <td align="center">model-13</td> 
   <td align="center">99.80</td> 
  </tr> 
  <tr> 
   <td align="center">model-13-conv</td> 
   <td align="center">99.86</td> 
  </tr> 
 </tbody> 
</table>

![这里写图片描述][70 2]  
![这里写图片描述][70 3]

### 部分代码 ###

# -*- coding: utf-8 -*-
    
    from keras.models import Sequential
    from keras.layers.core import Dense, Dropout, Flatten, Activation
    from keras.layers.convolutional import Conv2D, MaxPooling2D
    from keras.preprocessing.image import load_img, img_to_array
    from keras.utils import np_utils
    import os
    import numpy as np
    
    
    def load_dataset(filedir):
        """ 读取数据 :param filedir: :return: """
        image_data_list = []
        label = []
        train_image_list = os.listdir(filedir + '/train_data')
        for img in train_image_list:
            url = os.path.join(filedir + '/train_data/' + img)
            image = load_img(url, grayscale=True, target_size=(48, 48))
            #print(image.shape)
            image_data_list.append(img_to_array(image))
            label.append(img.split('.')[0].split("-")[1])
        img_data = np.array(image_data_list)
        img_data = img_data.astype('float32')
        img_data /= 255
        return img_data, label
    
    
    def make_network():
        model = Sequential()
        model.add(Conv2D(32, (3, 3), padding='same', input_shape=(48, 48, 1)))
        model.add(Activation('relu'))
        model.add(Conv2D(32, (3, 3)))
        model.add(Activation('relu'))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Dropout(0.5))
    
        model.add(Flatten())
        model.add(Dense(128))
        model.add(Activation('relu'))
        model.add(Dropout(0.5))
        model.add(Dense(7))
        model.add(Activation('softmax'))
    
        model.save('./data/model/model-basic.h5')
        return model
    
    
    if __name__ == '__main__':
        train_loss = []
        train_accuracy = []
        train_x, train_y = load_dataset('data')
        train_y = np_utils.to_categorical(train_y)
        model = make_network()
        model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy'])
        model.fit(train_x, train_y, batch_size=500, epochs=200, verbose=1)

[https_github.com_roguesir_DL-ML-project_tree_master_Expression-Recognition]: https://github.com/roguesir/DL-ML-project/tree/master/Expression-Recognition
[70]: /images/20220521/c18530d0e10d4f8bb91edb1ba78cbece.png
[70 1]: /images/20220521/5375f5e788b0463088bc44c74318dfc5.png
[70 2]: /images/20220521/3397614ac7a7431c916a1d3682c3a649.png
[70 3]: /images/20220521/93745a008d364bbc87a5565364a33ce5.png