Skip to content
2000
Volume 15, Issue 4
  • ISSN: 2210-3279
  • E-ISSN: 2210-3287

Abstract

Introduction

Face identification and tracking have grown in importance in a variety of applications, including security, surveillance, and human-computer interaction. The goal of this paper is to create a real-time face detection and tracking system that uses a 2D convolutional neural network (CNN) model.

Methods

The model is trained on a dataset of facial images with accompanying bounding boxes, allowing it to recognize and localize faces in real-time video streams with high accuracy for 3D.VGG16 is a well-known CNN architecture that has shown excellent performance in image classification applications. Additional layers are added to the network to modify VGG16 for face detection: a fully connected layer for classification and two fully connected levels for bounding box regression.

Results and Discussion

Facial expressions are a great way to guide cursor movement, with average accuracies of about 95% and 95.5% for 2D and 3D models, respectively. Head movements are an additional intriguing technique with an accuracy rate of about 93% for 2D on average. Eye movements can be used to precisely control the cursor with average accuracy rates of about 94% and 93.5% for 2D and 3D models, respectively.

Conclusion

The different CNN models were compared based on the accuracies out of which VGG16 results better. The accuracy improvement of 0.05% and 1.58% was observed for the 3D model over the 2D model for facial expressions and head movements, respectively.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/swcc/10.2174/0122103279343829241220205000
2025-01-29
2026-01-02

  • From This Site

    /content/journals/swcc/10.2174/0122103279343829241220205000
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. ViolaP. JonesM. Rapid object detection using a boosted cascade of simple features.IEEE Computer Society Conference on Computer Vision and Pattern RecognitionKauai, HI, USA2001II10.1109/CVPR.2001.990517
     [Google Scholar]
  2. Ming-HsuanYang KriegmanD.J. AhujaN. Detecting faces in images: A survey.IEEE Trans. Pattern Anal. Mach. Intell.2002241345810.1109/34.982883
     [Google Scholar]
  3. BelhumeurP.N. HespanhaJ.P. KriegmanD.J. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection.IEEE Trans. Pattern Anal. Mach. Intell.199719771172010.1109/34.598228
     [Google Scholar]
  4. GeC. LuoW. JiangY.G. CuiJ. 3D face reconstruction from a single depth image: A survey.IEEE Trans. Circ. Syst. Video Tech.201829823122333
     [Google Scholar]
  5. SaragihJ.M. GoeckeR. CohnJ.F. A nonlinear discriminative approach to AAM fitting.IEEE Trans. Pattern Anal. Mach. Intell.2011331121822195
     [Google Scholar]
  6. A toolkit for making real-world machine learning and data analysis applications.Available from: http://dlib.net
  7. AsthanaA. ZafeiriouS. ChengS. PanticM. Incremental face alignment in the wild.IEEE International Conference on Computer Vision (ICCV)Columbus, OH, USA201418591866
     [Google Scholar]
  8. ZhuX. LeiZ. YanJ. YiD. LiS.Z. High-fidelity pose and expression normalization for face recognition in the wild.IEEE Conference on Computer Vision and Pattern Recognition(CVPR)Boston, MA, USA2015787796
     [Google Scholar]
  9. BaltrušaitisT. MahmoudM. RobinsonP. Cross-dataset learning and person- specific normalisation for automatic Action Unit detection.IEEE International Conference on Computer Vision(ICCV)Ljubljana, Slovenia20151610.1109/FG.2015.7284869
     [Google Scholar]
  10. GuoY. ZhangL. HuY. HeX. GaoJ. MS-Celeb-1M: A dataset and benchmark for large-scale face recognition.European Conference on Computer Vision (ECCV)201821822195
     [Google Scholar]
  11. KazemiV. SullivanJ. One millisecond face alignment with an ensemble of regression trees.IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Columbus, OH, USA20141867187410.1109/CVPR.2014.241
     [Google Scholar]
  12. TranT.D. PhungD.Q. 3D face modeling from single frontal image by 3D morphable model.IEEE International Conference on Image Processing (ICIP)200681905
     [Google Scholar]
  13. HuberP. HuG. TenaR. MortazavianP. KoppenW.P. AnjosA. A multiresolution 3D morphable face model and fitting framework.European Conference on Computer Vision (ECCV)Rome, Italy201828922903
     [Google Scholar]
  14. PanticM. RothkrantzL.J.M. Expert system for automatic analysis of facial expressions.Image Vis. Comput.2000181188190510.1016/S0262‑8856(00)00034‑2
     [Google Scholar]
  15. AsthanaA. ZafeiriouS. ChengS. PanticM. StoicaA. From pixels to response maps: Discriminative image filtering for face alignment in the wild.IEEE Trans. Pattern Anal. Mach. Intell.2018401229072925 26357352
     [Google Scholar]
  16. McCoolM. ReindersJ. RobisonA. Structured Parallel Programming: Patterns for Efficient Computation.Elsevier2012881905
     [Google Scholar]
  17. DuanL. WangD. ZhengW.S. A survey on face recognition from low-quality images.IEEE Trans. Circ. Syst. Video Tech.2019293631648
     [Google Scholar]
  18. JourablooA. LiuX. Large-pose face alignment via CNN-based dense 3D model fitting.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Las Vegas, NV, USA20164188419610.1109/CVPR.2016.454
     [Google Scholar]
  19. CaoZ. SimonT. WeiS.E. SheikhY. Face alignment by explicit shape regression.IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2014881905
     [Google Scholar]
  20. SagonasC. AntonakosE. TzimiropoulosG. ZafeiriouS. PanticM. 300 faces in-the-wild challenge: The first facial landmark localization challenge.IEEE International Conference on Computer Vision(ICCV)Sydney, NSW, Australia2013397403
     [Google Scholar]
  21. LiuD. HuaG. WuD. FFA-Net: A novel network for facial feature points detection.IEEE Trans. Image Process.201625839373948
     [Google Scholar]
  22. ParkhiO.M. VedaldiA. ZissermanA. Deep face recognition.Proceedings of the British Machine Vision Conference(BMVC)201510.5244/c.29.41
     [Google Scholar]
  23. BansalA. CastilloC. RanjanR. ChellappaR. PatelV.M. The do’s and don’ts for CNN-based face verification.IEEE Trans. Pattern Anal. Mach. Intell.2018401128922903
     [Google Scholar]
  24. RanjanR. SankaranarayananS. CastilloC.D. ChellappaR. An all-in-one convolutional neural network for face analysis.IEEE Conference on Computer Vision and Pattern Recognition(CVPR)DC, USA20171724
     [Google Scholar]
  25. MasiI. TranA.T. HassnerT. LeksutJ.T. MedioniG. Do we really need to collect millions of faces for effective face recognition?European Conference on Computer Vision (ECCV)Amsterdam, The NetherlandsOctober 11-142892290310.1007/978‑3‑319‑46454‑1_35
     [Google Scholar]
  26. YangPingyang Lin Qiang YanShuicheng GengXiansheng Face detection in unconstrained images with multi-stage cascaded CNN architecture IEEE Trans Pattern Anal Mach2014
     [Google Scholar]
  27. NaoumiS. BazziA. BomfinR. ChafiiM. Complex neural network based Joint AoA and AoD estimation for bistatic ISAC.IEEE J. Sel. Top. Signal Process.202411510.1109/JSTSP.2024.3387299
     [Google Scholar]
  28. ChafiiM. BariahL. MuhaidatS. DebbahM. Twelve scientific challenges for 6G: Rethinking the foundations of communications theory.IEEE Commun. Surv. Tutor.202325286890410.1109/COMST.2023.3243918
     [Google Scholar]
  29. On outage-based beamforming design for dual-functional radar-communication 6G systems.IEEE Trans. Wirel. Commun.202311
     [Google Scholar]
  30. MuJ. ZhangR. CuiY. GaoN. JingX. UAV meets integrated sensing and communication: Challenges and future directions.IEEE Commun. Mag.2023615626710.1109/MCOM.008.2200510
     [Google Scholar]
  31. KumarV. ChafiiM. SwindlehurstA.L. TranL-N. FlanaganM.F. SCA-based beamforming optimization for IRS-Enabled secure integrated sensing and communication.IEEE Global Communications ConferenceKuala Lumpur, Malaysia20235992599710.1109/GLOBECOM54140.2023.10437283
     [Google Scholar]
  32. YangJian RenXuan ZhangXiaodong LiuTong Face++: A joint learning framework of face detection and face alignment IEEE Trans Pattern Anal Mach.2017
     [Google Scholar]
  33. GoyalH. SidanaK. SinghC. JainA. JindalS. A real time face mask detection system using convolutional neural network.Multimedia Tools Appl.20228111149991501510.1007/s11042‑022‑12166‑x 35233179
     [Google Scholar]
  34. AggarwalA. JainS. JindalH. Computational model for the detection of diabetic retinopathy in 2-D color fundus retina scan.Curr. Med. Imaging Rev.202420e1573405624818310.2174/0115734056248183231010111937 38333976
     [Google Scholar]
  35. BhardwajC. JainS. SoodM. Transfer learning based robust automatic detection system for diabetic retinopathy grading.Neural Comput. Appl.20213320139991401910.1007/s00521‑021‑06042‑2
     [Google Scholar]
  36. BhardwajC. JainS. SoodM. Deep learning–based diabetic retinopathy severity grading system employing quadrant ensemble model.J. Digit. Imaging202134244045710.1007/s10278‑021‑00418‑5 33686525
     [Google Scholar]
  37. DelamouM. ChafiiM. BazziA. AmhoudE.M. Deep learning-based estimation for multitarget radar detection.IEEE 97th Vehicular Technology Conference,. Florence, Italy20231510.1109/VTC2023‑Spring57618.2023.10200157
     [Google Scholar]
/content/journals/swcc/10.2174/0122103279343829241220205000
Loading
Facial Gesture Interfaces: Breaking Barriers for Individuals with Disabilities
Int J Sensors Wirel Commun Control 15, 329 (2025); https://doi.org/10.2174/0122103279343829241220205000
/content/journals/swcc/10.2174/0122103279343829241220205000
/content/journals/swcc/10.2174/0122103279343829241220205000
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): 3D implementation; CNN; face detection; hands-free; Mouseless; tracking

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test