A Lightweight Face Recognition Model based on MobileFaceNet for Limited Computation Environment
DOI:
https://doi.org/10.4108/eai.28-2-2022.173547Keywords:
Face recognition, MobileFaceNet, weak computing environment, channel attention mechanismAbstract
The face recognition method based on deep convolutional neural network is difficult to deploy in the embedding devices. In this work, we optimize the MobileFaceNet face recognition network MobileFaceNet so as to deploy it in embedding environment. Firstly, we reduce the model parameters by reducing the number of layers in MobileFaceNet. Then, the h-ReLU6 activation function is used to replace PReLU in the original model. Finally, the effective channel attention module efficient channel attention is introduced to obtain the importance of each feature channel by learning. After the optimization, the MobileFaceNet parameters are compressed to 3.4 MB,
which is smaller than the original model (4.9 MB), and the mAPs reach 98.52%, 97.54% and 91.33% on the test sets of LFW, VGGFace2 and the self-built database, respectively, and the recognition time is about 85 ms/photo. It shows that the proposed method achieves a good balance between the model complexity and model performance.
Downloads
References
Turk M, Pentland A. Eigenfaces for recognition[J]. Journal of cognitive neuroscience, 1991, 3(1): 71-86.
Wold S, Esbensen K, Geladi P. Principal component analysis[J]. Chemometrics and intelligent laboratory systems, 1987, 2(1): 37-52.
Belhumeur P N, Hespanha J P, Kriegman D J. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 19(7):711-720.
Wright J, Yi M, Mairal J, et al. Sparse Representation for Computer Vision and Pattern Recognition[J]. Proceedings of the IEEE, 2010, 98(6):p.1031-1044.
Li S, Deng D. Editorial: Smart Technologies Improve our Daily Lives[J]. EAI Endorsed Transactions on Internet of Things, 2019, 5(18):163845.
Krizhevsky A, Sutskever I, Hinton G. ImageNet Classification with Deep Convolutional Neural Networks[J]. Advances in neural information processing systems, 2012, 25(2).
TAIGMAN, YANIV, YANG, MING, RANZATO, MARC'AURELIO, et al. DeepFace: Closing the Gap to Human-Level Performance in Face Verification[C]. //2014 IEEE Conference on Computer Vision and Pattern Recognition: 2014 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), 23 -28 June 2014, Columbus, Ohio. 2014:1701-1708.
F Schroff, Kalenichenko D, Philbin J. FaceNet: a Unified Embedding for Face Recognition and Clustering[J]. IEEE, 2015.
Chen C, Cheng R. Improving Indoor Localization Based on Artificial Neural Network Technology[J]. EAI Endorsed Transactions on Internet of Things, 2018, 4(16):159633.
IANDOLA, FORREST N., HAN, SONG, MOSKEWICZ, MATTHEW W., et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size[J]. . 2016.
CHOLLET, FRANÇOIS. Xception: Deep Learning with Depthwise Separable Convolutions[J]. 2016.
Howard A G, Zhu M, Chen B, et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications[J]. 2017.
Sandler M, Howard A, Zhu M , et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Recognition (CVPR). IEEE, 2018.
CHEN S, LIU Y, GAO X, et al. MobileFaceNets: Efficient CNNs for accurate real-time face verification on mobile devices [C］// 1761 Journal of Beijing University of Aeronautics and Astronautics 2020 Chinese Conference on Biometric Recognition.Berlin: Springer, 2018: 428-438.
IOFFE, SERGEY, SZEGEDY, CHRISTIAN. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift[J]. 2015.
Zhang Z. H.,Wang R.. An improved face recognition method based on MobileFaceNet network[J]. Journal of Beijing University of Aeronautics and Astronautics,2020,46(9):1756-1762.DOI:10.13700/j.bh.1001-5965.2020.0049.
Lee H J, Kim H E, Nam H. SRM : A Style-based Recalibration Module for Convolutional Neural Networks[J]. 2019.
Zhang X, Zhao R, Qiao Y, et al. AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
Li Hang. Design and implementation of a lightweight face recognition system based on MobileFaceNet [D]. Southwest University, 2020. DOI:10.27684/d.cnki.gxndx.2020.001575.
Jie H, Li S, Gang S , et al. Squeeze-and-Excitation Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, PP(99).
Deng J, Guo J, Zafeiriou S. ArcFace: Additive Angular Margin Loss for Deep Face Recognition[J]. 2018.
Wang Bihao. Research and optimization of face screening algorithm [D]. University of Electronic Science and Technology,2019.
Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
ZHAO, QI, LIU, JIAHUI, ZHANG, BOXUE, et al. Interpretable Relative Squeezing bottleneck design for compact convolutional neural networks model[J]. Image and vision computing,2019,89(Sep.):276-288. DOI:10.1016/j.imavis.2019.06.006.
Chen Y, Peng F, Kang X, et al. Depthwise Separable Convolutional Neural Network for Image Forensics[C]// 2019 IEEE Visual Communications and Image Processing (VCIP). IEEE, 2019.
Haykin S S , Gwynn R. Neural Networks and Learning Machines [M]. China Machine Press, 2009.
Grimstad B, Andersson H. ReLU Networks as Surrogate Models in Mixed-Integer Linear Programs[J]. Computers & Chemical Engineering, 2019, 131(Dec.5):106580.1-106580.15.
Morrison A F, Epifanovsky E, Herbert J M. Double-buffered, heterogeneous CPU + GPU integral digestion algorithm for single- excitation calculations involving a large number of excited states[J]. Journal of Computational Chemistry, 2018, 39(26).
Petersen P, Voigtlaender F. Optimal approximation of piecewise smooth functions using deep ReLU neural networks[J]. 2017.
Lecun Y, Bengio Y , Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436.
Ghimire D, Jeong S, Joonwhoan Lee.... Facial expression recognition based on local region specific features and support vector machines[J]. Multimedia Tools & Applications, 2017, 76(6):7803-7821.
Jie, Shen, Samuel, et al. Squeeze-and-Excitation Networks.[J]. IEEE transactions on pattern analysis and machine intelligence, 2019.
Seo S, Ki S, Kim M. A Novel Just-Noticeable-Difference-based Saliency-Channel Attention Residual Network for Full-Reference Image Quality Predictions[J]. 2019.
Dong Y, Zhen L, Liao S, et al. Learning Face Representation from Scratch[J]. Computer Science, 2014.
Kaziakhmedov E, Kireev K, Melnikov G, et al. Real-world attack on MTCNN face detection system[C]// 2019.
Huang G B, Mattar M, Berg T, et al. Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments[J]. Month, 2008.
Cao Q, Shen L, Xie W, et al. VGGFace2: A dataset for recognising faces across pose and age[C]// IEEE Computer Society. IEEE Computer Society, 2017.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 EAI Endorsed Transactions on Internet of Things
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 3.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
Funding data
-
Scientific Research Foundation of Hunan Provincial Education Department
Grant numbers 21B0833
