Comparative Evaluation of Machine Learning Algorithms for Affective State Recognition from Children's Drawings

TL;DR

This study compares deep learning models for recognizing children's emotional states from drawings, focusing on performance, robustness, and efficiency to aid early ASD assessment.

Contribution

It provides a systematic comparison of MobileNet, EfficientNet, and VGG16 for affective state recognition from children's drawings using transfer learning.

Findings

Deeper models like VGG16 achieve higher accuracy but are less efficient.

Lightweight models like MobileNet offer better speed and suitability for mobile applications.

Trade-offs between model complexity and performance are highlighted for real-time affective computing.

Abstract

Autism spectrum disorder (ASD) represents a neurodevelopmental condition characterized by difficulties in expressing emotions and communication, particularly during early childhood. Understanding the affective state of children at an early age remains challenging, as conventional assessment methods are often intrusive, subjective, or difficult to apply consistently. This paper builds upon previous work on affective state recognition from children's drawings by presenting a comparative evaluation of machine learning models for emotion classification. Three deep learning architectures -- MobileNet, EfficientNet, and VGG16 -- are evaluated within a unified experimental framework to analyze classification performance, robustness, and computational efficiency. The models are trained using transfer learning on a dataset of children's drawings annotated with emotional labels provided by psychological experts. The results highlight important trade-offs between lightweight and deeper architectures when applied to drawing-based affective computing tasks, particularly in mobile and real-time application contexts.