Sistem Registrasi Dan Identifikasi Wajah Untuk Akses Fasilitas Universitas Kristen Petra Dengan Kombinasi Facenet Dan Hierarchical Navigable Small Worlds

August Berlin Tungka


The Identity Cards of students are used to access the facilities and participate in events of Petra Christian University. The problem which arises from these cards is the misuse by the irresponsible group. For this, the university needs the face identification system as the alternative. This thesis is meant to build a fast, accurate, and easy to use face identification system. The methods used to solve the problem is a combination of Facenet and Hierarchical Navigable Small Worlds (HNSW). Facenet is used to process the face into a 128-dimension vector which will be used for searching. HNSW is a k Nearest Neighbor search method which is used in a large-scale search. Using the method, the system takes an average time of 1 second to identify faces.


Face detection; face recognition; Facenet; Hierarchical Navigable Small worlds; HNSW

Full Text:



Adjabi, I., Ouahabi, A., Benzaoui, A, & Taleb-Ahmed, A.

(2020). Past, Present, and Future of Face Recognition: A

Review. Electronics, 9 (8), 1188. DOI:


Aumüller, M., Bernhardsson, E., & Faithfull, A. (2020).

ANN-Benchmarks: A benchmarking tool for approximate

nearest neighbor algorithms. Information Systems, 87,

DOI: 10.1016/

Malkov, Y. A. & Yashunin, D. A. (2018). Efficient and robust

approximate nearest neighbor search using hierarchical

navigable small world graphs. IEEE Transactions on Pattern

Analysis and Machine Intelligence, 42 (4), 824-836. DOI:


Mei, W & Weihong, D. (2021). Deep face recognition: A

survey. Neurocomputing, 429, 215-244. DOI:


Ranjan, R. et al. (2018). Deep learning for understanding

Faces: machines may be just as good, or better, than humans.

IEEE Signal Processing Magazine, 35 (1), 66-83. DOI:


Schroff, F., Kalenichenko, D., Philbin, J. (2015). FaceNet: A

unified embedding for face recognition and clustering. Paper

presented at Proceedings of the 2015 IEEE Conference on

Computer Vision and Pattern Recognition (CVPR), Boston,

MA, USA (pp. 815–823). DOI:


Wen, L. et al. (2019). Approximate nearest neighbor search

on high dimensional data — experiments, analyses, and

improvement. IEEE Transactions on Knowledge and Data

Engineering, 32 (8), 1475 - 1488. DOI:



  • There are currently no refbacks.

Jurnal telah terindeks oleh :