Facial Expression Recognition at the Edge: CPU vs GPU vs VPU vs TPU
Open Access
- 5 June 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 243-248
Abstract
Facial Expression Recognition (FER) plays an important role in human-computer interactions and is used in a wide range of applications. Convolutional Neural Networks (CNN) have shown promise in their ability to classify human facial expressions, however, large CNNs are not well-suited to be implemented on resource-and energy-constrained IoT devices. In this work, we present a hierarchical framework for developing and optimizing hardware-aware CNNs tuned for deployment at the edge. We perform a comprehensive analysis across various edge AI accelerators including NVIDIA Jetson Nano, Intel Neural Compute Stick, and Coral TPU. Using the proposed strategy, we achieved a peak accuracy of 99.49% when testing on the CK+ facial expression recognition dataset. Additionally, we achieved a minimum inference latency of 0.39 milliseconds and a minimum power consumption of 0.52 Watts.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Using a Social Robot to Evaluate Facial Expressions in the WildSensors, 2020
- Facial Expression Recognition Using Computer Vision: A Systematic ReviewApplied Sciences, 2019
- A Survey of Convolutional Neural Networks on Edge with Reconfigurable ComputingAlgorithms, 2019
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search2019
- Learning Transferable Architectures for Scalable Image Recognition2018
- Hyper-parameter selection in deep neural networks using parallel particle swarm optimization2017
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision ApplicationsarXiv, 2017
- Going deeper in facial expression recognition using deep neural networks2016
- Hyperopt: a Python library for model selection and hyperparameter optimizationComputational Science & Discovery, 2015
- The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression2010