Skip to main content

Face Recognition Efficiency Enhancements Using Tensorflow and WebAssembly: A Practical Approach

  • 190 Accesses

Part of the Communications in Computer and Information Science book series (CCIS,volume 1478)

Abstract

In this research paper we have studied the use of WebAssembly technology applied to the problem of facial recognition in real world Human-Computer Interaction (HCI) applications. Multiple parameters determining the system were tested using a large image data set. Experiments have shown how, with careful choice of system parameters, very high levels of accuracy can be achieved for large populations, even using only a few pre-stored images per person. In addition, a web application was developed to compare the efficiency of facial recognition using different backends of Tensorflow.js in the browser. The results show that WebAssembly technology is perfectly operational for use in this area and provides user experience improvements in terms of efficiency and stability. In the coming months, WebAssembly is expected to incorporate two relevant developments: Single Instruction Multiple Data (SIMD) and Multithreading (MT). Our experiments show that by enabling these features WebAssembly can provide a very suitable technical solution for in-browser face recognition.

Keywords

  • Webassembly
  • Wasm
  • Face recognition
  • Tensorflow

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-92325-9_7
  • Chapter length: 14 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   64.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-92325-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   84.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.

References

  1. Sanchez, V., Pfeiffer, C., Skeie, N.-O.: A review of smart house analysis methods for assisting older people living alone. J. Sens. Actuator Netw. 6(3), 11 (2017)

    CrossRef  Google Scholar 

  2. Haas, A., et al.: Bringing the web up to speed with WebAssembly. In: Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation (2017). https://doi.org/10.1145/3062341.3062363

  3. TensorFlow: Tensorflow.org. https://www.tensorflow.org/. Accessed 28 Apr 2021

  4. OpenCV – OpenCV: Opencv.org, 09 Feb 2021. https://opencv.org/. Accessed 28 Apr 2021

  5. Amazon Rekognition: Amazon.com. https://aws.amazon.com/es/rekognition/. Accessed 28 Apr 2021

  6. Vision AI: Google.com. https://cloud.google.com/vision/. Accessed: 28 Apr 2021

  7. Youssef, A.E.: Exploring cloud computing services and applications, Psu.edu. https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.649.485&rep=rep1&type=pdf. Accessed 28 Apr 2021

  8. Zhou, M., Zhang, R., Xie, W., Qian, W., Zhou, A.: Security and privacy in cloud computing: a survey. In: 2010 Sixth International Conference on Semantics, Knowledge and Grids, pp. 105–112 (2010). https://doi.org/10.1109/SKG.2010.19

  9. Taheri, S., Vedienbaum, A., Nicolau, A., Hu, N., Haghighat, M.R.: OpenCV.js: computer vision processing for the open web platform. In: Proceedings of the 9th ACM Multimedia Systems Conference (2018). https://doi.org/10.1145/3204949.3208126

  10. Gerard, C.: TensorFlow.js. In: Practical Machine Learning in JavaScript, pp. 25–43. Apress, Berkeley (2021)

    Google Scholar 

  11. WebAssembly: Webassembly.org. https://webassembly.org/. Accessed 28 Apr 2021

  12. Herrera, D., Chen, H., Lavoie, E., Hendren, L.: Numerical computing on the web: benchmarking for the future. In: Proceedings of the 14th ACM SIGPLAN International Symposium on Dynamic Languages (2018). https://doi.org/10.1145/3276945.3276968

  13. WebAssembly proposals. https://github.com/WebAssembly/proposals. Accessed 28 Apr 2021

  14. Jibaja, I., et al.: Vector parallelism in JavaScript: language and compiler support for SIMD. In: 2015 International Conference on Parallel Architecture and Compilation (PACT), pp. 407–418 (2015). https://doi.org/10.1109/PACT.2015.33

  15. Green, I.: Web Workers: Multithreaded Programs in JavaScript. O’Reilly Media, Sebastopol (2012)

    Google Scholar 

  16. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)

    Google Scholar 

  17. Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: VGGFace2: a dataset for recognising faces across pose and age. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 67–74 (2018). https://doi.org/10.1109/FG.2018.00020

  18. Mühler, V.: face-api.js. https://github.com/justadudewhohacks/face-api.js. Accessed 30 Apr 2021

  19. King, D.E.: dlib-models. https://github.com/davisking/dlib-models. Accessed 30 Apr 2021

  20. Serkan, K., et al.: 1D convolutional neural networks and applications: a survey. Mech. Syst. Signal Process. 151, 107398 (2021). https://doi.org/10.1016/j.ymssp.2020.107398

    CrossRef  Google Scholar 

  21. Waseem, R., Zenghui, W.: Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput. 29(9), 2352–2449 (2017). https://doi.org/10.1162/neco_a_00990

    MathSciNet  CrossRef  MATH  Google Scholar 

  22. Simone, B., et al.: Benchmark analysis of representative deep neural network architectures. https://doi.org/10.1109/ACCESS.2018.2877890

  23. Learn Artificial Intelligence: Course, Deep Reinforcement Learning Free; CV, Self Attention. Best deep CNN architectures and their principles: from AlexNet to EfficientNet

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ricardo Martín Manso .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Martín Manso, R., Escrivá Gallardo, P. (2021). Face Recognition Efficiency Enhancements Using Tensorflow and WebAssembly: A Practical Approach. In: Ruiz, P.H., Agredo-Delgado, V., Kawamoto, A.L.S. (eds) Human-Computer Interaction. HCI-COLLAB 2021. Communications in Computer and Information Science, vol 1478. Springer, Cham. https://doi.org/10.1007/978-3-030-92325-9_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-92325-9_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-92324-2

  • Online ISBN: 978-3-030-92325-9

  • eBook Packages: Computer ScienceComputer Science (R0)