Multicultural Facial Expression Recognition Based on Differences of Western-Caucasian and East-Asian Facial Expressions of Emotions

Benitez-Garcia, Gibran; Nagaoka, Tomoaki; Kaneko, Masahide

doi:10.1587/transinf.2017mvp0025

Cited by 10 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the identical manner, the authors in [34] trained their model using different datasets such as the CK+, JAFFE, and BU-3DFE so that they can predict facial emotions on them. We can find similar work in [35] where the authors presented an analysis of Western Caucasian and East Asian facial expressions of emotions based on visual representations and cross-cultural FER, and in [36], the authors proposed a joint deep learning approach called racial identity aware deep convolutional neural network, one developed to recognize multicultural facial expressions.…”

Section: Related Workmentioning

confidence: 95%

Ethical AI in facial expression analysis: racial bias

Sham

Aktas

Rizhinashvili

et al. 2022

SIViP

View full text Add to dashboard Cite

Facial expression recognition using deep neural networks has become very popular due to their successful performances. However, the datasets used during the development and testing of these methods lack a balanced distribution of races among the sample images. This leaves a possibility of the methods being biased toward certain races. Therefore, a concern about fairness arises, and the lack of research aimed at investigating racial bias only increases the concern. On the other hand, such bias in the method would decrease the real-world performance due to the wrong generalization. For these reasons, in this study, we investigated the racial bias within popular state-of-the-art facial expression recognition methods such as Deep Emotion, Self-Cure Network, ResNet50, InceptionV3, and DenseNet121. We compiled an elaborated dataset with images of different races, cross-checked the bias for methods trained, and tested on images of people of other races. We observed that the methods are inclined towards the races included in the training data. Moreover, an increase in the performance increases the bias as well if the training dataset is imbalanced. Some methods can make up for the bias if enough variance is provided in the training set. However, this does not mitigate the bias completely. Our findings suggest that an unbiased performance can be obtained by adding the missing races into the training data equally. KeywordsFacial expression recognition (FER) • Deep neural networks • Reaction emotion • LSTM Abdallah Hussein Sham and Kadir Aktas are both equally led this work.Our thanks to Pexels API for granting us the rights for the data collection of the database.

show abstract

Section: Related Workmentioning

confidence: 95%

Ethical AI in facial expression analysis: racial bias

Sham

Aktas

Rizhinashvili

et al. 2022

SIViP

View full text Add to dashboard Cite

show abstract

“…PCA algorithm is used to match sub-regions against sub-patterns. Classification is done using k-nearest neighbor [9]. We learn how machine learning methods, e. g convolution neural networks, can progress the Facial expression recognition correctness in biometric applications.…”

Section: Literature Reviewmentioning

confidence: 99%

Recognizing Facial Expressions Across Cultures Using Gradient Features

Akram¹,

Tariq²,

Ali³

et al. 2023

JICET

View full text Add to dashboard Cite

The goal of this research is to provide a useful technique for better facial emotion recognition, especially across cultural boundaries. Although people communicate both verbally and nonverbally, face expressions are crucial in determining verbal communication. The previous human-computer interface did not take into account thus much nonverbal communication. We need a system that can recognise and comprehend the intentions and feelings expressed by social and cultural cues. In this article, we present a technique for categorising facial photos into six different categories of expressions. Three phases make up the approach; in the first, we used viola Jones to edit off all but the face from the original image and create new ones. Then a HOG histogram was used to extract gradient characteristics. Last but not least, we used SVM to classify picture characteristics and got encouraging results. Comparing the outcomes of the suggested method to other cutting-edge approaches, they are astounding. With regard to combined cross-cultural datasets, it offers accuracy of 99.97%.

show abstract

“…Previous research has shown that movement can affect human emotions, meaning that an ERS needs to consider a larger number of complex factors, such as the motion of soldiers or individual physiological differences. The authors in [62] analyze the differences in emotional expression among people in a cross-cultural population from the perspective of visual representation. The results show that an ERS based on facial features cannot universally apply to a military with a multi-racial culture.…”

Section: Systematic Analysis Of Framework Unitsmentioning

confidence: 99%

Systematic Analysis of a Military Wearable Device Based on a Multi-Level Fusion Framework: Research Directions

Shi

Zhang

Liu

et al. 2019

Sensors

View full text Add to dashboard Cite

With the development of the Internet of Battlefield Things (IoBT), soldiers have become key nodes of information collection and resource control on the battlefield. It has become a trend to develop wearable devices with diverse functions for the military. However, although densely deployed wearable sensors provide a platform for comprehensively monitoring the status of soldiers, wearable technology based on multi-source fusion lacks a generalized research system to highlight the advantages of heterogeneous sensor networks and information fusion. Therefore, this paper proposes a multi-level fusion framework (MLFF) based on Body Sensor Networks (BSNs) of soldiers, and describes a model of the deployment of heterogeneous sensor networks. The proposed framework covers multiple types of information at a single node, including behaviors, physiology, emotions, fatigue, environments, and locations, so as to enable Soldier-BSNs to obtain sufficient evidence, decision-making ability, and information resilience under resource constraints. In addition, we systematically discuss the problems and solutions of each unit according to the frame structure to identify research directions for the development of wearable devices for the military.

show abstract

Multicultural Facial Expression Recognition Based on Differences of Western-Caucasian and East-Asian Facial Expressions of Emotions

Cited by 10 publications

References 21 publications

Ethical AI in facial expression analysis: racial bias

Ethical AI in facial expression analysis: racial bias

Recognizing Facial Expressions Across Cultures Using Gradient Features

Systematic Analysis of a Military Wearable Device Based on a Multi-Level Fusion Framework: Research Directions

Contact Info

Product

Resources

About