Analysis of the Use of MTCNN and Landmark Technology to Improve the Accuracy of Facial Recognition on Official Documents

Ferri Rama Chandra; Hajra Rasmita Ngemba; Odai Amer Hamid; Nouval Trezandy Lapatta; Syaiful Hendra; Deny Wiria Nugraha; Syahrullah Syahrullah

doi:10.30871/jaic.v9i1.8814

Ferri Rama Chandra Informatics Engineering, Faculty of Engineering, Tadulako University
Hajra Rasmita Ngemba Information Systems, Faculty of Engineering, Tadulako University
Odai Amer Hamid College of Technical Management Mosul, Northern Technical University
Nouval Trezandy Lapatta Informatics Engineering, Faculty of Engineering, Tadulako University
Syaiful Hendra Informatics Engineering, Faculty of Engineering, Tadulako University
Deny Wiria Nugraha Informatics Engineering, Faculty of Engineering, Tadulako University
Syahrullah Syahrullah Information Systems, Faculty of Engineering, Tadulako University

DOI: https://doi.org/10.30871/jaic.v9i1.8814

Keywords: Facial Detection, Facial Landmark, Face Recognition, MTCNN

Abstract

A face recognition system consists of two stages: face detection and face recognition. Detection of features such as eyes and mouth is important in facial image processing, especially for official documents such as identity cards. To ensure identification accuracy, this research applies facial landmark extraction technology and MTCNN (Multi-Task Cascaded Convolutional Neural Network). The purpose of this research is to evaluate the accuracy of MTCNN in detecting facial features at the Department of Population and Civil Registration (dukcapil) Palu City, using facial landmarks and waterfall methods as an application development methodology. The evaluation results show that MTCNN has high face recognition accuracy and good positioning ability regardless of what GPU in use as long have right CPU and System Operation. In comparison, the Viola-Jones algorithm is effective for high-speed applications, while SSD offers balanced performance with GPU device requirements for optimal performance. While MTCNN proved to be effective, challenges still exist, such as false positives and false negatives, especially in poor lighting conditions and extreme poses. Image and camera quality, including resolution and facial expression, also affects detection accuracy. These findings suggest that the application of MTCNN can improve face recognition accuracy for official documents, although it requires addressing existing challenges. With this technology, it is expected that errors in facial recognition can be minimized, resulting in more reliable data that meets the standards for issuing identity documents. This research contributes to the development of a more accurate and efficient face recognition system for personal identification applications.

Downloads

Download data is not yet available.

References

M. Andrejevic, C. O'Neill, G. Smith, N. Selwyn, and X. Gu, “Granular biopolitics: Facial recognition, pandemics and the securitization of circulation,” New Media Soc, vol. 26, no. 3, pp. 1204–1226, March. 2024, doi 10.1177/14614448231201638.

K. Pandey, R. Lilani, P. Naik, and G. Pol, “Human Face Recognition Using Image Processing.” doi: 10.17577/IJERTCONV2IS04051.

R. Neha and S. Nithin, “Comparative Analysis of Image Processing Algorithms for Face Recognition,” in 2018 International Conference on Inventive Research in Computing Applications (ICIRCA), IEEE, Jul. 2018, pp. 683–688. doi: 10.1109/ICIRCA.2018.8597309.

KD Anggara, DP Kartikasari, and FA Bakhtiar, “Implementation of MTCNN Algorithm in Facial Recognition-based Authentication Mechanism,” 2023. [Online]. Available: http://j-ptiik.ub.ac.id

I. Adjabi, A. Ouahabi, A. Benzaoui, and A. Taleb-Ahmed, “Past, Present, and Future of Face Recognition: A Review,” Electronics (Basel), vol. 9, no. 8, p. 1188, Jul. 2020, doi: 10.3390/electronics9081188.

M. Kim, Y. Cho, and S.Y. Kim, “Effects of diagnostic regions on facial emotion recognition: The moving window technique,” Front Psychol, vol. 13, Sept. 2022, doi: 10.3389/fpsyg.2022.966623.

I. Kumaran et al., "Face Recognition Using Measurement-Based Approach and Segmentation Method in Multiple Positions and Lighting," FIDELITY: Jurnal Teknik Elektro, vol. 3, no. 1, pp. 5–8, Jan. 2021, doi: 10.52005/fidelity.v3i1.85.

F. Alanazi, G. Ushaw, and G. Morgan, “Improving Detection of DeepFakes through Facial Region Analysis in Images,” Electronics (Basel), vol. 13, no. 1, p. 126, Dec. 2023, doi: 10.3390/electronics13010126.

N. Zhang, J. Luo, and W. Gao, “Research on Face Detection Technology Based on MTCNN,” in 2020 International Conference on Computer Network, Electronic, and Automation (ICCNEA), IEEE, Sep. 2020, pp. 154–158. doi: 10.1109/ICCNEA50255.2020.00040.

A. Ghofrani, RM Toroghi, and S. Ghanbari, “Realtime Face-Detection and Emotion Recognition Using MTCNN and miniShuffleNet V2,” in 2019 5th Conference on Knowledge-Based Engineering and Innovation (KBEI), IEEE, Feb. 2019, pp. 817–821. doi: 10.1109/KBEI.2019.8734924.

Y. Wu and Q. Ji, “Facial Landmark Detection: A Literature Survey,” Int J Comput Vis, vol. 127, no. 2, pp. 115–142, Feb. 2019, doi: 10.1007/s11263-018-1097-z.

D. Lydia and Z. Astuti, Study of Facial Expression Recognition using PCA and CNN Methods. 2018.

T. Devries, K. Biswaranjan, and G. W. Taylor, “Multi-task Learning of Facial Landmarks and Expressions,” in 2014 Canadian Conference on Computer and Robot Vision, IEEE, May 2014, pp. 98–103. doi: 10.1109/CRV.2014.21.

K. Khabarlak and L. Koriashkina, “Fast Facial Landmark Detection and Applications: A Survey,” J Comput Sci Technol, vol. 22, no. 1, p. e02, Apr. 2022, doi: 10.24215/16666038.22.e02.

C. Zhongshan, F. Xinning, A. Manickam, and V.E. Sathishkumar, “RETRACTED ARTICLE: Facial landmark detection using artificial intelligence techniques,” Ann Oper Res, vol. 326, no. S1, pp. 63–63, Jul. 2023, doi: 10.1007/s10479-021-04355-y.

S. Abidin et al., “Face Detection Using Webcam-Based Haar Cascade Classifier Method in Matlab”.

Y. Said and M. Barr, “Human emotion recognition based on facial expressions via deep learning on high-resolution images,” Multimed Tools Appl, vol. 80, no. 16, pp. 25241–25253, Jul. 2021, doi: 10.1007/s11042-021-10918-9.

RR Hajar et al., “Facial Landmark Based Face Detection Using OpenCV and DLIB,” Jurnal Teknologi Informasi (Journal of Information Technology), vol. 5, no. 2, 2021.

Z. Zhou, H. Li, H. Liu, N. Wang, G. Yu, and R. Ji, “STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2023, pp. 15475–15484. doi: 10.1109/CVPR52729.2023.01485.

MH Robin, Md. M. Ur Rahman, AM Taief, and Q. Nahar Eity, “Improvement of Face and Eye Detection Performance by Using Multi-task Cascaded Convolutional Networks,” in 2020 IEEE Region 10 Symposium (TENSYMP), IEEE, 2020, pp. 977–980. doi: 10.1109/TENSYMP50017.2020.9230756.

NG Arsandy, J. Maulindar, and Moh. Muhtarom, "Implementation of Employee Attendance with Face Recognition using Waterfall Method in Solo Technopark," International Journal Software Engineering and Computer Science (IJSECS), vol. 4, no. 2, pp. 680–689, Aug. 2024, doi: 10.35870/ijsecs.v4i2.2617.

IM Revina and WRS Emmanuel, “A Survey on Human Face Expression Recognition Techniques,” Journal of King Saud University - Computer and Information Sciences, vol. 33, no. 6, pp. 619–628, Jul. 2021, doi: 10.1016/j.jksuci.2018.09.002.

P. Chandran, D. Bradley, M. Gross, and T. Beeler, "Attention-Driven Cropping for Very High-Resolution Facial Landmark Detection," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2020, pp. 5860–5869. doi: 10.1109/CVPR42600.2020.00590.

NK Benamara et al., “Real-time facial expression recognition using smoothed deep neural network ensemble,” Integr Comput Aided Eng, vol. 28, no. 1, pp. 97–111, Dec. 2020, doi: 10.3233/ICA-200643.

RD Djohari, HR Ngemba, S. Hendra, DS Angraeni, NT Lapatta, and DW Nugraha, "Employee Attendance System with Facial Recognition Technology Using a Single Shot Detector (SSD) Algorithm," Journal Of Informatics And Telecommunication Engineering, vol . 7, no. 2, pp. 424–434, Jan. 2024, doi: 10.31289/jite.v7i2.10869.