Face Detection and Recognition Using MTCNN and FaceNet

Year : 2024 | Volume : 11 | Issue : 02 | Page : 132 140
    By

    Sahil Bisht,

  • Sonal Fatangare,

  • Apeksha Patil,

  • Aakanksha Panadi,

  • Dev Kulkarni,

  1. Student, Department of Computer Engineering, Rasiklal M. Dhariwal Sinhgad Technical Institutes Campus, Pune, Maharashtra, India
  2. Assistant Professor, Department of Computer Engineering, Rasiklal M. Dhariwal Sinhgad Technical Institutes Campus, Pune, Maharashtra, India
  3. Student, Department of Computer Engineering, Rasiklal M. Dhariwal Sinhgad Technical Institutes Campus, Pune, Maharashtra, India
  4. Student, Department of Computer Engineering, Rasiklal M. Dhariwal Sinhgad Technical Institutes Campus, Pune, Maharashtra, India
  5. Student, Department of Computer Engineering, Rasiklal M. Dhariwal Sinhgad Technical Institutes Campus, Pune, Maharashtra, India

Abstract

Face detection and face recognition are major tasks in the field of computer vision with several real-world applications and many products being developed in the same field. This study gives a detailed implementation of the product that is developed for accurate detection and recognition of faces along with audio output of the face detected. This development would act as a base for a few future products that can be developed for the visually impaired community. For the development of the product, a thorough survey was done from classical methods, such as eigenfaces and Fisher faces, to cutting-edge deep learning techniques, such as advanced convolutional neural networks analyzing various face detection and recognition algorithms and the challenges associated with them, like changing lighting scenarios, obstructed views, and pose fluctuations. Generally, Convolutional Neural Networks (CNNs) are employed in developing such products. However, instead of utilizing general CNN, this product utilizes specific algorithms, namely Multi-Task Cascaded Convolutional Neural network (MTCNN) for face detection and FaceNet for face recognition respectively which are based on CNN itself. The model is trained on images of different persons which helps in extracting the required facial features. Finally, when the program is run, the detected face is shown with a green bounding box and the name of the person detected at the right bottom of the bounding box. Also, an audio output is provided by the system giving the name of the detected person. If no person is detected, then “Unknown” is the audio output given. This product gives a high accuracy due to extra filter layers in both MTCNN and FaceNet which helps in refining the training process and improving the efficiency of the system.

Keywords: Face recognition, face detection, convolutional neural network (CNN), deep learning, MTCNN, FaceNet, industrial applications

[This article belongs to Journal of Artificial Intelligence Research & Advances ]

How to cite this article:
Sahil Bisht, Sonal Fatangare, Apeksha Patil, Aakanksha Panadi, Dev Kulkarni. Face Detection and Recognition Using MTCNN and FaceNet. Journal of Artificial Intelligence Research & Advances. 2024; 11(02):132-140.
How to cite this URL:
Sahil Bisht, Sonal Fatangare, Apeksha Patil, Aakanksha Panadi, Dev Kulkarni. Face Detection and Recognition Using MTCNN and FaceNet. Journal of Artificial Intelligence Research & Advances. 2024; 11(02):132-140. Available from: https://journals.stmjournals.com/joaira/article=2024/view=155859


References

  1. Tyagi R, Tomar GS, Baik N. A survey of unconstrained face recognition algorithm and its applications. Int J Secur Appl. 2016 Dec 1; 10(12): 369–76.
  2. Ku H, Dong W. Face recognition based on mtcnn and convolutional neural network. Front Signal Process. 2020 Jan; 4(1): 37–42.
  3. Manzoor S, Kim EJ, Joo SH, Bae SH, In GG, Joo KJ, Choi JH, Kuc TY. Edge deployment framework of guardbot for optimized face mask recognition with real-time inference using deep learning. Ieee 2022 Jul 25; 10: 77898–921.
  4. Singh AP, Singh V. Infringement of Prevention Technique against Keyloggers using Sift Attack. In 2018 IEEE International Conference on Advanced Computation and Telecommunication (ICACAT). 2018 Dec 28; 1–4.
  5. Hashmi SA. Face Detection in Extreme Conditions: A Machine-learning Approach. arXiv preprint arXiv:2201.06220. 2022 Jan 17.
  6. Islam MT, Ahmed T, Rashid AR, Islam T, Rahman MS, Habib MT. Convolutional neural network based partial face detection. In 2022 IEEE 7th International conference for Convergence in Technology (I2CT). 2022 Apr 7; 1–6.
  7. Soni L, Waoo A. A Review of Recent Advances Methodologies for Face Detection. Int J Curr Eng Technol. 2023; 13(02): 86–92.
  8. Jin Rongrong, et al. (2021). Face recognition based on MTCNN and Facenet. [Online]. Available from: https://jasonyanglu.github.io/files/lecture_notes/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0_2020/Project/Face%20Recognition%20Based%20on%20MTCNN%20and%20FaceNet.pdf
  9. Dang TV, Tran HL. A Secured, Multilevel Face Recognition based on Head Pose Estimation, MTCNN and FaceNet. Journal of Robotics and Control (JRC). 2023 Jun 20; 4(4): 431–7.
  10. Khan MZ, Harous S, Hassan SU, Khan MU, Iqbal R, Mumtaz S. Deep unified model for face recognition based on convolution neural network and edge computing. IEEE Access. 2019 May 23; 7: 72622–33.
  11. Peralta B, Figueroa A, Nicolis O, Trewhela Á. Gender identification from community question answering avatars. IEEE Access. 2021 Nov 23; 9: 156701–16.
  12. Wang Dalin, Rongfeng Li. Enhancing Accuracy of Face Recognition in Occluded Scenarios with OAM-Net. IEEE Access. 2023; 11: 117297–117307.
  13. Li L, Liu M, Sun L, Li Y, Li N. ET-YOLOv5s: toward deep identification of students’ in-class behaviors. IEEE Access. 2022 Apr 22; 10: 44200–11.
  14. Tripathy R, Daschoudhury R. Real-time face detection and tracking using haar classifier on soc. International Journal of Electronics and Computer Science Engineering (IJECSE). 2014; 3(2):175–84.
  15. Hussain D, Ismail M, Hussain I, Alroobaea R, Hussain S, Ullah SS. Face Mask Detection Using Deep Convolutional Neural Network and MobileNetV2‐Based Transfer Learning. Wirel Commun Mob Comput. 2022; 2022(1): 1536318.
  16. Kaur G, Sinha R, Tiwari PK, Yadav SK, Pandey P, Raj R, Vashisth A, Rakhra M. Face mask recognition system using CNN model. Neuroscience Informatics. 2022 Sep 1; 2(3): 100035.
  17. Mo H, Kim S. A deep learning-based human identification system with wi-fi csi data augmentation. IEEE Access. 2021 Jun 25; 9: 91913–20.
  18. Coe J, Atay M. Evaluating impact of race in facial recognition across machine learning and deep learning algorithms. Computers. 2021 Sep 10; 10(9): 113.
  19. Rajyalakshmi V, Lakshmanna K. Intelligent face recognition based multi-location linked IoT based car parking system. IEEE Access. 2023 Aug 7; 11: 84258–84269.
  20. Raghavendra M, Neha R, et al. Missing Child Identification using Convolutional Neural Network. Int J Res Appl Sci Eng Technol (IJRASET). 2024; 186(16): 380–384.
  21. Samatha Naidu DJ, Lokesh R. Missing Child Identification System using Deep Learning with VGG-FACE Recognition Technique. International Journal of Computer Science and Engineering (IJCSE). 2022; 9(9): 1–11.
  22. Zahid SM, Najesh TN, Ameen SR, Ali A.s A Multi Stage Approach for Object and Face Detection using CNN. In 2023 IEEE 8th International Conference on Communication and Electronics Systems (ICCES). 2023 Jun 1; 798–803.
  23. Osorio-Roig D, Rathgeb C, Drozdowski P, Busch C. Stable hash generation for efficient privacy-preserving face identification. IEEE Trans Biom Behav Identity Sci. 2021 Jul 28; 4(3): 333–48.
  24. Viola P, Jones MJ. Robust real-time face detection. Int J Comput Vis. 2004 May; 57(2): 137–54.
  25. Ibrahim AA, Nisar K, Hzou YK, Welch I. Review and analyzing RFID technology tags and applications. In 2019 IEEE 13th international conference on application of information and communication technologies (AICT). 2019 Oct 23; 1–4.
  26. Liu X, Xie X, Zhao X, Wang K, Li K, Liu AX, Guo S, Wu J. Fast identification of blocked RFID tags. IEEE Trans Mob Comput. 2018 Jan 15; 17(9): 2041–54.
  27. Hegde N, Preetha S, Bhagwat S. Facial Expression Classifier Using Better Technique: FisherFace Algorithm. In 2018 IEEE International Conference on Advances in Computing, Communications and Informatics (ICACCI). 2018 Sep 19; 604–610.
  28. Belhumeur PN, Hespanha JP, Kriegman DJ. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. In Computer Vision—ECCV’96: 4th European Conference on Computer Vision Cambridge, UK, April 15–18, 1996 Proceedings. Springer Berlin Heidelberg. 1996; 43–58.
  29. Taheri S, Vedienbaum A, Nicolau A, Hu N, Haghighat MR. Opencv.js: Computer vision processing for the open web platform. In Proceedings of the 9th ACM multimedia systems conference. 2018 Jun 12; 478–483.
  30. Viola P, Jones M. Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition (CVPR 2001) 2001 Dec 8; 1: I–I.
  31. Lu WY, Ming YA. Face detection based on viola-jones algorithm applying composite features. In 2019 IEEE International Conference on Robots & Intelligent System (ICRIS). 2019 Jun 15; 82–85.
  32. Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell. 1989 Jul; 11(7): 674–93.
  33. Mulyono IUW, Susanto A, Rachmawanto EH, Fahmi A. Performance Analysis of Face Recognition using Eigenface Approach. In: 2019 IEEE International Seminar on Application for Technology of Information and Communication (iSemantic). 2019; 12–16.
Regular Issue Subscription Original Research
Volume 11
Issue 02
Received 28/05/2024
Accepted 05/07/2024
Published 10/07/2024
920

Login


My IP

PlumX Metrics