基于深度时空域卷积神经网络的表情识别模型  

Facial expression recognition model based on deep spatiotemporal convolutional neural networks

作　　者：杨格兰[1,2] 邓晓军[3] 刘琮[1] 

机构地区：[1]同济大学电子与信息工程学院,上海201804 [2]湖南城市学院信息科学与工程学院,湖南益阳413000 [3]湖南工业大学计算机与通信学院,湖南株洲412007

出　　处：《中南大学学报（自然科学版）》2016年第7期2311-2319,共9页Journal of Central South University:Science and Technology

基　　金：湖南省自然科学基金资助项目(2015JJ2046);湖南省教育厅优秀青年项目(12B023)~~

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。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.

关 键 词：情感计算 表情识别 时空域 卷积神经网络 深度学习 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]