Masked face recognition with convolutional visual self-attention network

Liu, Hui; Du, Ji-Xiang; Li, Zehua; Wei, Yuheng

doi:10.1016/j.neucom.2022.10.025

Cited by 20 publications

(8 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, one limitation of our work is that the accuracy of facial occlusion localization is affected by the 3D face alignment performance. In future work, we will consider improving the localization performance of occlusion face alignment [66] and explore new network architectures [67,68] to improve the recognition accuracy of occluded faces.…”

Section: Discussionmentioning

confidence: 99%

A 3D Occlusion Facial Recognition Network Based on a Multi-Feature Combination Threshold

Zhu

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

In this work, we propose a 3D occlusion facial recognition network based on a multi-feature combination threshold (MFCT-3DOFRNet). First, we design and extract the depth information of the 3D face point cloud, the elevation, and the azimuth angle of the normal vector as new 3D facially distinctive features, so as to improve the differentiation between 3D faces. Next, we propose a multi-feature combinatorial threshold that will be embedded at the input of the backbone network to implement the removal of occlusion features in each channel image. To enhance the feature extraction capability of the neural network for missing faces, we also introduce a missing face data generation method that enhances the training samples of the network. Finally, we use a Focal-ArcFace loss function to increase the inter-class decision boundaries and improve network performance during the training process. The experimental results show that the method has excellent recognition performance for unoccluded faces and also effectively improves the performance of 3D occlusion face recognition. The average Top-1 recognition rate of the proposed MFCT-3DOFRNet for the Bosphorus database is 99.52%, including 98.94% for occluded faces and 100% for unoccluded faces. For the UMB-DB dataset, the average Top-1 recognition rate is 95.08%, including 93.41% for occluded faces and 100% for unoccluded faces. These 3D face recognition experiments show that the proposed method essentially meets the requirements of high accuracy and good robustness.

show abstract

Section: Discussionmentioning

confidence: 99%

A 3D Occlusion Facial Recognition Network Based on a Multi-Feature Combination Threshold

Zhu

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Considering that the original Transformer may ignore the inter-patch information, Face Transformer modifies the patch generation process and makes the tokens with sliding patches that overlap each other. Inspired by the successful application of self-attention in computer vision, authors of [48] proposed a convolutional visual self-attention network (CVSAN), which uses self-attention to improve convolutional operators. A study conducted by [7] revealed the existence of racial bias in face recognition algorithms, resulting in significant performance degradation in real-world face recognition systems.…”

Section: Face Recognition In Special Scenesmentioning

confidence: 99%

Face-Inception-Net for Recognition

Zhang,

Wang,

Zhang

et al. 2024

Electronics

View full text Add to dashboard Cite

Face recognition in general scenarios has been saturated in recent years, but there is still room to enhance model performance in extreme scenarios and fairness situations. Inspired by the successful application of Transformer and ConvNet in computer vision, we propose a FIN-Block, which gives a more flexible composition paradigm for building a novel pure convolution model and provides a foundation for constructing a new framework for general face recognition in both extreme scenarios and fairness situations. FIN-Block-A uses a combination of stacked large-size convolution kernels and parallel convolution branches to ensure a large spatial receptive field while improving the module’s deep feature embedding and extraction capabilities. FIN-Block-B takes advantage of stacked orthogonal convolution kernels and parallel branches to balance model size and performance. By applying FIN-Block with an adapted convolution kernel size in different stages, we built a reasonable and novel framework Face-Inception-Net, and the performance of the model is highly competitive with ConvNeXt and InceptionNeXt. The models were trained on CASIA-WebFace and MS-wo-RFW databases and evaluated on 14 mainstream benchmarks, including LFW, extreme scene, and fairness test sets. The proposed Face-Inception-Net achieved the highest average TAR@FAR0.001 of 95.9% in all used benchmarks, fully demonstrating effectiveness and generality in various scenarios.

show abstract

“…Moreover, a convolutional visual self-attention network [ 32 ] is utilized as a masked face recognition method. The authors propose an attention mechanism that focuses on the visible regions of the face while considering the occluded areas due to masks.…”

Section: Related Workmentioning

confidence: 99%

Innovative Hybrid Approach for Masked Face Recognition Using Pretrained Mask Detection and Segmentation, Robust PCA, and KNN Classifier

Eman

Mahmoud

Ibrahim

et al. 2023

Sensors

View full text Add to dashboard Cite

Face masks are widely used in various industries and jobs, such as healthcare, food service, construction, manufacturing, retail, hospitality, transportation, education, and public safety. Masked face recognition is essential to accurately identify and authenticate individuals wearing masks. Masked face recognition has emerged as a vital technology to address this problem and enable accurate identification and authentication in masked scenarios. In this paper, we propose a novel method that utilizes a combination of deep-learning-based mask detection, landmark and oval face detection, and robust principal component analysis (RPCA) for masked face recognition. Specifically, we use pretrained ssd-MobileNetV2 for detecting the presence and location of masks on a face and employ landmark and oval face detection to identify key facial features. The proposed method also utilizes RPCA to separate occluded and non-occluded components of an image, making it more reliable in identifying faces with masks. To optimize the performance of our proposed method, we use particle swarm optimization (PSO) to optimize both the KNN features and the number of k for KNN. Experimental results demonstrate that our proposed method outperforms existing methods in terms of accuracy and robustness to occlusion. Our proposed method achieves a recognition rate of 97%, which is significantly higher than the state-of-the-art methods. Our proposed method represents a significant improvement over existing methods for masked face recognition, providing high accuracy and robustness to occlusion.

show abstract

Masked face recognition with convolutional visual self-attention network

Cited by 20 publications

References 74 publications

A 3D Occlusion Facial Recognition Network Based on a Multi-Feature Combination Threshold

A 3D Occlusion Facial Recognition Network Based on a Multi-Feature Combination Threshold

Face-Inception-Net for Recognition

Innovative Hybrid Approach for Masked Face Recognition Using Pretrained Mask Detection and Segmentation, Robust PCA, and KNN Classifier

Contact Info

Product

Resources

About