Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Facial Expression Recognition Using Residual Masking Network

Luan Pham, The Huynh Vu, Tuan Anh Tran

TL;DR

A novel Masking Idea is proposed to boost the performance of CNN in facial expression task that uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions.

Abstract

Automatic facial expression recognition (FER) has gained much attention due to its applications in human-computer interaction. Among the approaches to improve FER tasks, this paper focuses on deep architecture with the attention mechanism. We propose a novel Masking idea to boost the performance of CNN in facial expression task. It uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions. In experiments, we combine the ubiquitous Deep Residual Network and Unet-like architecture to produce a Residual Masking Network. The proposed method holds state-of-the-art (SOTA) accuracy on the well-known FER2013 and private VEMO datasets. The source code is available at https://github.com/phamquiluan/ResidualMaskingNetwork.

Facial Expression Recognition Using Residual Masking Network

TL;DR

A novel Masking Idea is proposed to boost the performance of CNN in facial expression task that uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions.

Abstract

Automatic facial expression recognition (FER) has gained much attention due to its applications in human-computer interaction. Among the approaches to improve FER tasks, this paper focuses on deep architecture with the attention mechanism. We propose a novel Masking idea to boost the performance of CNN in facial expression task. It uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions. In experiments, we combine the ubiquitous Deep Residual Network and Unet-like architecture to produce a Residual Masking Network. The proposed method holds state-of-the-art (SOTA) accuracy on the well-known FER2013 and private VEMO datasets. The source code is available at https://github.com/phamquiluan/ResidualMaskingNetwork.
Paper Structure (12 sections, 2 equations, 8 figures, 4 tables)

This paper contains 12 sections, 2 equations, 8 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related works
  3. Proposed method
  4. Overview
  5. Residual Masking Block
  6. Ensemble Method
  7. Experimental results
  8. Dataset
  9. Experiment setup
  10. Visual result explanation
  11. Evaluation and Analysis
  12. Conclusion

Figures (8)

  • Figure 1: Example of landmark detections and features of Masking Block as follows: landmark detection, original image, feature map before the $3^{rd}$ Masking Block, feature map after the $3^{rd}$ Masking Block.
  • Figure 2: The overview of Residual Masking Network.
  • Figure 3: Example images of two datasets.
  • Figure 4: The statistics of training, validation, and testing set.
  • Figure 5: The framework structure of the experiment setup.
  • ...and 3 more figures