Pengenalan Wajah Dengan Face-Api.js Berbasis CNN dan Geolokasi Menggunakan Equirectangular Approximation

Bimo Akbar Fadli(1*),Edy Winarno(2)
(1) Universitas Stikubank Semarang
(2) Universitas Stikubank Semarang
(*) Corresponding Author
DOI : 10.35889/progresif.v19i2.1398


Computer vision usag on an attendance system role is to make sure that the attendance cannot be done by another person. Besides that, the attendance system could also use  geolocation to determine the attendee location and the supposed attendance location. These process takes a considerable amount of server resource. To reduce the load of a server, a client side process could be used. Face recognition is done by using face-api.js which is a javascript module build on top of tensoflow.js core that implements some CNN (Convolutional Neural Networks) to detect, recognize, and extract feature of a face, that is optimized for website and mobile device. For the calculation of geolocation coordinate an equirectangular approximation formula is used. The accuracy of face recognition ranges between 93% to 97% and the geolocation calculation takes around 0.008300000003ms to complete.

Key words: Face Detection; Geolocation; Tensorflow; Attendance 



Penggunaan computer vision pada sistem absensi berperan sebagai pengaman untuk memastikan bahwa absensi tidak dapat diwakilkan oleh orang lain. Selain itu pada sistem absensi juga dapat ditambahkan sistem geolokasi untuk menentukan jarak pelaku dari jarak lokasi yang sudah ditentukan. Proses-proses tersebut memakan sumber daya besar pada server. Dengan mendelegasikan proses tersebut kepada klien, beban serer akan berkurang secara signifikan. Pengenalan wajah dilakukan dengan menerapkan face-api.js yang merupakan sebuah modul javascript yang dibangun diatas tensorflow.js core, yang mengimplementasikan beberapa CNN (Convolutional Neural Networks) untuk melakukan deteksi, pengenalan, dan deteksi fitur-fitur wajah, yang dioptimalkan untuk web dan perangkat mobile. Untuk geolokasi pengukuran jarak koordinat, digunakan formula equirectangular approximation. Dari penerapan pengenalan wajah dan geolokasi tersebut didapatkan akurasi pengenalan wajah berkisar antara 93% hingga 97% dan geolokasi menggunakan equirectangular approximation berjalan dalam waktu rata-rata 0.008300000003ms.

Kata kunci: Pengenalan wajah; Geolokasi; Tensorflow; Presensi


D. Yadav, S. Maniar, K. Sukhani, and K. Devadkar, In-Browser Attendance System using Face Recognition and Serverless Edge Computing. Institute of Electrical and Electronics Engineers Inc., 2021.

A. Hermawan, L. Lianata, Junaedi, and A. R. K. Maranto, ‘Implementasi Machine Learning Sebagai Pengenal Nominal Uang Rupiah dengan Metode YOLOv3’, SATIN - Sains dan Teknologi Informasi, vol. 8, no. 1, pp. 12–22, 2022.

E. Winarno, I. H. A. Amin, H. Februariyanti, P. W. Adi, W. Hadikurniawati, and M. T. Anwar, Attendance System Based on Face Recognition System Using CNN-PCA Method and Real-Time Camera. Institute of Electrical and Electronics Engineers Inc., 2019.

I. E. Hendarawan, ‘Vehicle Tire Crack Classification Using ResNet50 Architecture’, SATIN - Sains dan Teknologi Informasi, vol. 9, no. 1, Dec. 2022.

D. Frenza and R. Mukhaiyar, ‘Aplikasi Pengenalan Wajah Menggunakan Metode Adaptive Resonance Theory (ART)’, Ranah Research : Journal Of Multidisciplinary Research and Development, vol. 3, no. 3, pp. 147–153, 2021.

N. Wayan Wardani and M. Yoka Fathoni, ‘Perancangan Absensi Berbasis Face Recognition Pada Desa Sokaraja Lor Menggunakan Platform Android’, Jurnal Teknik Informatika dan Sistem Informasi, vol. 8, no. 1, pp. 91–104, 2021.

C. Gabriel and E. Sandoval, ‘Multiple Face Detection and Recognition System Design Applying Multiple Face Detection and Recognition System Design Applying Deep Learning in Web Browsers using JavaScript Deep Learning in Web Browsers using JavaScript Multiple Face Detection and Recognition System Design Applying Deep Learning in Web Browsers using JavaScript’. 2019.

Vincent Mühler, ‘face-api.js — JavaScript API for Face Recognition in the Browser with tensorflow.js’, ITNEXT. 2018.

S. Lukas, A. R. Mitra, R. I. Desanti, and D. Krisnadi, Student attendance system in classroom using face recognition technique. Institute of Electrical and Electronics Engineers Inc., 2016.

D. Sunaryono, J. Siswantoro, and R. Anggoro, ‘An android based course attendance system using face recognition’, Journal of King Saud University - Computer and Information Sciences, vol. 33, no. 3, pp. 304–312, 2021.

H. Yang and X. Han, ‘Face Recognition Attendance System Based on Real-Time Video Processing’, IEEE Access, vol. 8, pp. 159143–159150, 2020.

A. M. Morar, L. Efleih-Hassan, and D. Lungeanu, ‘Apparent Patterns in Ambulance Response Time in Timişoara’, 2020.

S. Shaikh, A. Matono, and K.-S. Kim, A Distance-Window Based Real-Time Processing of Spatial Data Streams. 2019.

M. Asadul Hoque, X. Hong, and B. Dixon, ‘Analysis of Mobility Patterns for Urban Taxi Cabs’, Applied Medical Informatics, vol. 42, no. 1, pp. 28–35, 2020.

K. Okokpujie, E. Noma-Osaghae, S. John, K.-A. Grace, and I. Okokpujie, A face recognition attendance system with GSM notification. 2017.

How To Cite This :


  • There are currently no refbacks.