Skip to main navigation Skip to search Skip to main content

Lightweight CNN Benchmarks for Facial Emotion Recognition in Pepper Robot Applications

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

69 Downloads (Pure)

Abstract

This work benchmarks three lightweight CNNs, MobileNetV2, EfficientNet-B0, and ResNet18, on a balanced AffectNet subset, evaluating accuracy, inference speed, and model size. Results show that lightweight CNNs provide competitive accuracy and efficiency, supporting their use in real-time applications.
Original languageEnglish
Title of host publicationIrish Machine Vision and Image Processing Conference 2025
PublisherIrish Pattern Recognition and Classification Society
Pages268 - 271
Number of pages4
ISBN (Electronic)978-0-9934207-9-5
Publication statusPublished (in print/issue) - 1 Sept 2025
EventIMVIP 2025 - Ulster University, Derry~Londonderry, Northern Ireland, Londonderry, United Kingdom
Duration: 1 Sept 20253 Sept 2025
https://imvipconference.github.io/

Conference

ConferenceIMVIP 2025
Country/TerritoryUnited Kingdom
CityLondonderry
Period1/09/253/09/25
Internet address

Bibliographical note

Paper accepted and presented at IMVIP 2025

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 3 - Good Health and Well-being
    SDG 3 Good Health and Well-being

Keywords

  • imaging
  • Machine Vision
  • Emotion Recognition
  • Deep Learning
  • Lightweight CNN

Fingerprint

Dive into the research topics of 'Lightweight CNN Benchmarks for Facial Emotion Recognition in Pepper Robot Applications'. Together they form a unique fingerprint.

Cite this