An Adversarial Attacks Resistance-based Approach to Emotion Recognition from Images using Facial Landmarks | IEEE Conference Publication | IEEE Xplore

An Adversarial Attacks Resistance-based Approach to Emotion Recognition from Images using Facial Landmarks


Abstract:

Emotion recognition has become an increasingly important area of research due to the increasing number of CCTV cameras in the past few years. Deep network-based methods h...Show More

Abstract:

Emotion recognition has become an increasingly important area of research due to the increasing number of CCTV cameras in the past few years. Deep network-based methods have made impressive progress in performing emotion recognition-based tasks, achieving high performance on many datasets and their related competitions such as the ImageNet challenge. However, deep networks are vulnerable to adversarial attacks. Due to their homogeneous representation of knowledge across all images, a small change to the input image made by an adversary might result in a large decrease in the accuracy of the algorithm. By detecting heterogeneous facial landmarks using the machine learning library Dlib we hypothesize we can build robustness to adversarial attacks. The residual neural network (ResNet) model has been used as an example of a deep learning model. While the accuracy achieved by ResNet showed a decrease of up to 22%, our proposed approach has shown strong resistance to an attack and showed only a little (< 0.3%) or no decrease when the attack is launched on the data. Furthermore, the proposed approach has shown considerably less execution time compared to the ResNet model.
Date of Conference: 31 August 2020 - 04 September 2020
Date Added to IEEE Xplore: 14 October 2020
ISBN Information:

ISSN Information:

Conference Location: Naples, Italy
Citations are not available for this document.

I. INTRODUCTION

Emotion recognition is an important area of research that has gained attention in the last two decades [1]. Information like nonverbal signals in human to human communication can be transmitted by facial expression [2], [3]. For instance, information can be conveyed via a scowl or a smile. It is considered as a natural way of trying to understand the psychological state of people during communication [4].

Cites in Papers - |

Cites in Papers - IEEE (6)

Select All
1.
Harisu Abdullahi Shehu, Will N. Browne, Hedwig Eisenbarth, "Attention-Based Methods for Emotion Categorization From Partially Covered Faces", IEEE Transactions on Emerging Topics in Computational Intelligence, vol.8, no.1, pp.1057-1070, 2024.
2.
Qixuan Zhang, Zhifeng Wang, Yang Liu, Zhenyue Qin, Kaihao Zhang, Tom Gedeon, "Geometric-Aware Facial Landmark Emotion Recognition", 2023 6th International Conference on Software Engineering and Computer Science (CSECS), pp.1-6, 2023.
3.
Souha Ayadi, Zied Lachiri, "Deep Neural Network for visual Emotion Recognition based on ResNet50 using Song-Speech characteristics", 2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET), pp.363-368, 2022.
4.
Harisu Abdullahi Shehu, Will N. Browne, Hedwig Eisenbarth, "An Out-of-Distribution Attack Resistance Approach to Emotion Categorization", IEEE Transactions on Artificial Intelligence, vol.2, no.6, pp.564-573, 2021.
5.
Harisu Abdullahi Shehu, Will Browne, Hedwig Eisenbarth, "Particle Swarm Optimization for Feature Selection in Emotion Categorization", 2021 IEEE Congress on Evolutionary Computation (CEC), pp.752-759, 2021.
6.
Peng Wang, Bing Xue, Mengjie Zhang, Jing Liang, "A Grid-dominance based Multi-objective Algorithm for Feature Selection in Classification", 2021 IEEE Congress on Evolutionary Computation (CEC), pp.2053-2060, 2021.

Cites in Papers - Other Publishers (5)

1.
Jesús Jaime Moreno Escobar, Oswaldo Morales Matamoros, Erika Yolanda Aguilar del Villar, Hugo Quintana Espinosa, Liliana Chanona Hernández, "DS-CNN: Deep Convolutional Neural Networks for Facial Emotion Detection in Children with Down Syndrome during Dolphin-Assisted Therapy", Healthcare, vol.11, no.16, pp.2295, 2023.
2.
Akhilesh Kumar, Awadhesh Kumar, "Analysis of Machine Learning Algorithms for Facial Expression Recognition", Advanced Network Technologies and Intelligent Computing, vol.1534, pp.730, 2022.
3.
Harisu Abdullahi Shehu, Will N. Browne, Hedwig Eisenbarth, "An anti-attack method for emotion categorization from images", Applied Soft Computing, vol.128, pp.109456, 2022.
4.
Harisu Abdullahi Shehu, Abubakar Siddique, Will N. Browne, Hedwig Eisenbarth, "Lateralized Approach for Robustness Against Attacks in Emotion Categorization from Images", Applications of Evolutionary Computation, vol.12694, pp.469, 2021.
5.
Harisu Abdullahi Shehu, Will Browne, Hedwig Eisenbarth, "Emotion Categorization from Video-Frame Images Using a Novel Sequential Voting Technique", Advances in Visual Computing, vol.12510, pp.618, 2020.

Contact IEEE to Subscribe

References

References is not available for this document.