计算机与现代化Issue(1)：84-87,4.DOI:10.3969/j.issn.1006-2475.2015.01.017
一种基于深度学习的表情识别方法
A Facial Expression Recognition Method Based on Deep Learning
王剑云 1李小霞2
作者信息
- 1. 特殊环境机器人技术四川省重点实验室，四川 绵阳 621010
- 2. 西南科技大学信息工程学院，四川 绵阳 621010
- 折叠
摘要
Abstract
According to the problem that traditional facial expression recognition method could not act a robust performance , we propose an algorithm based on deep learning .First of all, we train two sparse auto encoder in two scales , and the parameter of the hidden layer should be a series of convolutional kernel , we use these kernels to extract first-layer features .Then we get second-layer features through max-pooling operators , it improves the invariance of the features .Finally we parallelize seven four-layers neural networks to accomplish the recognition task .The experiment result shows this deep neural networks structure act a robust perform-ance in facial expression recognition task in the case of the test samples ’ ID information did not appear in the training samples .关键词
表情识别/深度学习/神经网络/稀疏自编码Key words
facial expression recognition/deep learning/neural networks/auto sparse encoder分类
信息技术与安全科学引用本文复制引用
王剑云,李小霞..一种基于深度学习的表情识别方法[J].计算机与现代化,2015,(1):84-87,4.
