Learning Facial Expression Codes with Sparse Auto-Encoder
Learning Facial Expression Codes with Sparse Auto-Encoder
复制标题
DOI：
10.4028/www.scientific.net/amm.433-435.334
复制
发表时间：
2013-10
期刊：
影响因子：
--
通讯作者：
D. Hu;G. Duan
中科院分区：
文献类型：
--
作者：
D. Hu;G. Duan
训练稀疏自编码器模型提取不同面部表情的编码，该模型包括4个编码器层和3个解码层，位于第4层（编码层）的表示是期望的特征。从训练面中随机选择大量的patch，首先通过反向传播最小化无监督稀疏重建误差对模型进行训练，然后学习softmax分类器进行监督分类。分类的输入向量是由学习稀疏自编码器和卷积和池化两个关键操作生成的人脸图像特征。该模型每层隐藏单元数量较少，训练集数量相对较少，在实验中取得了优异的性能。
A sparse auto-encoder model was trained to extract the code of different facial expression, which comprises four encoder layers and three decode layers, the representation locating in the fourth layer (code layer) is the features expected. With large amounts of patches randomly selected from training faces, the model was trained firstly via backpropagation which minimizes an unsupervised sparse reconstruction error, and then a softmax classifier was learned for supervised classification. The input vector for the classification is the feature of facial image induced by the learned sparse auto-encoder and two key operations (convolving and pooling). Using a small number of hidden units per layer and a relatively small number of training set, the proposed model achieves excellent performance in the experiments.