Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition

Frontiers in Psychology

Min Peng¹ 

关键词: micro-expression recognition;    deep learning;    optical flow;    convolutional neural network;    feature fusion;   

DOI  :  10.3389/fpsyg.2017.01745

学科分类：心理学（综合）

来源: Frontiers

【 摘 要 】

Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of stream of DTSCNN is used to adapt to different frame rate of micro-expression video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the overfitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II) showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve.

【 授权许可】

CC BY