Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Emotion Classification of Children Expressions

Sanchayan Vivekananthan

TL;DR

The model designed using Batch Normalisation, Dropout, and SE Attention mechanisms for the classification of children's emotions achieved an accuracy rate of 89\% due to these methods improving the precision of emotion recognition in children.

Abstract

This paper proposes a process for a classification model for the facial expressions. The proposed process would aid in specific categorisation of children's emotions from 2 emotions namely 'Happy' and 'Sad'. Since the existing emotion recognition systems algorithms primarily train on adult faces, the model developed is achieved by using advanced concepts of models with Squeeze-andExcitation blocks, Convolutional Block Attention modules, and robust data augmentation. Stable Diffusion image synthesis was used for expanding and diversifying the data set generating realistic and various training samples. The model designed using Batch Normalisation, Dropout, and SE Attention mechanisms for the classification of children's emotions achieved an accuracy rate of 89\% due to these methods improving the precision of emotion recognition in children. The relative importance of this issue is raised in this study with an emphasis on the call for a more specific model in emotion detection systems for the young generation with specific direction on how the young people can be assisted to manage emotions while online.

Emotion Classification of Children Expressions

TL;DR

The model designed using Batch Normalisation, Dropout, and SE Attention mechanisms for the classification of children's emotions achieved an accuracy rate of 89\% due to these methods improving the precision of emotion recognition in children.

Abstract

This paper proposes a process for a classification model for the facial expressions. The proposed process would aid in specific categorisation of children's emotions from 2 emotions namely 'Happy' and 'Sad'. Since the existing emotion recognition systems algorithms primarily train on adult faces, the model developed is achieved by using advanced concepts of models with Squeeze-andExcitation blocks, Convolutional Block Attention modules, and robust data augmentation. Stable Diffusion image synthesis was used for expanding and diversifying the data set generating realistic and various training samples. The model designed using Batch Normalisation, Dropout, and SE Attention mechanisms for the classification of children's emotions achieved an accuracy rate of 89\% due to these methods improving the precision of emotion recognition in children. The relative importance of this issue is raised in this study with an emphasis on the call for a more specific model in emotion detection systems for the young generation with specific direction on how the young people can be assisted to manage emotions while online.

Paper Structure

This paper contains 33 sections, 4 equations, 10 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Need for children’s expression focused model
  3. Literature Review
  4. Available Child Facial Expression Datasets
  5. Role of Synthetic Data in Enhancing Datasets
  6. Methodology
  7. Image Collection
  8. Image Synthesis
  9. Generative Adversarial Network (GAN)
  10. Variational Auto Encoder (VAE)
  11. Stable diffusion
  12. Advanced Image Synthesis with Grounded DINO, SAM and Stable Diffusion in-painting
  13. Data Augmentation
  14. Need for Data Augmentation
  15. Data Augmentation methods for emotion detection
  16. ...and 18 more sections

Figures (10)

  • Figure 1: Sample images from the dataset collected from the internet
  • Figure 2: Generative Adversarial Network (GAN) Architecture. Reprinted from Vivekananthan (2024).
  • Figure 3: Samples of the synthesized images using GAN technique
  • Figure 4: Variational Auto Encoder (VAE) Architecture.Reprinted from Vivekananthan (2024)
  • Figure 5: Samples of the synthesised images using VAE technique
  • ...and 5 more figures