基于深度时空域卷积神经网络的表情识别模型

来源期刊:中南大学学报(自然科学版)2016年第7期

论文作者:杨格兰 邓晓军 刘琮

文章页码:2311 - 2320

关键词:情感计算;表情识别;时空域;卷积神经网络;深度学习

Key words:affect computing; facial expression recognition; spatiotemporal space; convolutional neural networks; deep learning

摘    要:基于特征抽取是表情识别算法中的重要步骤,但是现有算法依赖手工设计特征且适应性差等问题,提出基于深度时空域卷积神经网络的表情识别模型,采用数据驱动策略直接从表情视频中自动抽取时空域中的动静态特征。使用新颖的卷积滤波器响应积替代权重和,使得模型能同时抽取到动态特征和静态特征。引入深度学习的多层设计,使得模型能逐层学习到更抽象、更宏观的特征。采用端对端的有监督学习策略,使得所有参数在同一目标函数下优化。研究结果表明:训练后的卷积核类似于Garbor滤波器的形态,这与视觉皮层细胞对激励的响应相似;该模型能对表情视频进行更准确分类;通过与其他几种近年出现的算法进行比较,验证该算法的优越性。

Abstract: Considering that the feature extraction is crucial phases in the process of facial recognition, and it incorporates manual intervention that hinders the development of reliable and accurate algorithms, in order to describe facial expression in a data-driven fashion, a temporal extension of convolutional neural network was developed to exploit dynamics of facial expressions and improve performance. The model was fundamental on the multiplicative interactions between convolutional outputs, instead of summing filter responses, and the responses were multiplied. The developed approach was capable of extracting features not only relevant to facial motion, but also sensitive to the appearance and texture of the face. The introduction of hierarchical structure from deep learning makes the approach learn the high-level and global features. The end to end training strategy optimizes all the parameters under the uniform objective. The results show that the approach extracts the two types of features simultaneously as natural outcome of the developed architecture. The learnt fitters are similar to the receptive field area of visual cortex. The model is proved to be effective.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号