Non-Linearities Improve OrigiNet based on Active Imaging for Micro Expression Recognition

TL;DR

This paper introduces OrigiNet, a shallow CNN with a novel RReLU activation and active imaging, to improve micro expression recognition by better capturing subtle facial dynamics and spatial-temporal features.

Contribution

The paper proposes a new shallow CNN architecture called OrigiNet with a refined RReLU activation and active imaging for enhanced micro expression recognition.

Findings

Outperforms state-of-the-art methods on four ME datasets

Achieves higher accuracy with less computational complexity

Effectively captures subtle micro-expression features

Abstract

Micro expression recognition (MER)is a very challenging task as the expression lives very short in nature and demands feature modeling with the involvement of both spatial and temporal dynamics. Existing MER systems exploit CNN networks to spot the significant features of minor muscle movements and subtle changes. However, existing networks fail to establish a relationship between spatial features of facial appearance and temporal variations of facial dynamics. Thus, these networks were not able to effectively capture minute variations and subtle changes in expressive regions. To address these issues, we introduce an active imaging concept to segregate active changes in expressive regions of a video into a single frame while preserving facial appearance information. Moreover, we propose a shallow CNN network: hybrid local receptive field based augmented learning network (OrigiNet) that efficiently learns significant features of the micro-expressions in a video. In this paper, we propose a new refined rectified linear unit (RReLU), which overcome the problem of vanishing gradient and dying ReLU. RReLU extends the range of derivatives as compared to existing activation functions. The RReLU not only injects a nonlinearity but also captures the true edges by imposing additive and multiplicative property. Furthermore, we present an augmented feature learning block to improve the learning capabilities of the network by embedding two parallel fully connected layers. The performance of proposed OrigiNet is evaluated by conducting leave one subject out experiments on four comprehensive ME datasets. The experimental results demonstrate that OrigiNet outperformed state-of-the-art techniques with less computational complexity.