Emotion differentiation based on arousal intensity estimation from facial expressions

Document Type

Conference Item

Publication Date

1-1-2020

Abstract

Emotion recognition still remains a research issue that can be improved significantly. This paper worked on it using facial feature extraction followed by arousal level estimation. We extracted facial features via four Convolutional Neural Networks (CNNs) pre-trained on ImageNet: ResNet152V2, Xception, ResNeXt101, and InceptionResNetV2 based on low memory usage and modernity. For estimating arousal levels, Exponential Linear Unit (ELU) was compared with Rectified Linear Unit (ReLU) in a custom deep model framework. Wild facial expression image data was taken from the relatively new AffectNet database. Up to this point, recognition of emotions from AffectNet is largely treated as a classification problem, with arousal level estimation mostly unexplored. Our results showed that the custom deep model trained on multiple classes and fine-tuned on one class was more effective than that trained and tested on the same class. ResNet152V2 displayed the best performance among the CNNs, emphasizing its suitability for the CultureNet-based architecture from which this algorithm is based. Further research includes more activation functions, ResNet variants, and the application of a softmax layer.

Keywords

Facial expressions, Convolutional neural networks, Continuous dimensional space

Divisions

ai

Volume

621

Publisher

SPRINGER-VERLAG SINGAPORE PTE LTD

Publisher Location

152 BEACH ROAD, #21-01/04 GATEWAY EAST, SINGAPORE, 189721, SINGAPORE

Event Title

iCatse International Conference on Information Science and Applications (ICISA)

Event Location

Seoul, South Korea

Event Dates

16-18 December 2019

Event Type

conference

Additional Information

iCatse International Conference on Information Science and Applications (ICISA), Seoul, South Korea, Dec 16-18, 2019

This document is currently not available here.

Share

COinS