Article Per Year (5 Year)
p-Index From 2021 - 2026
1.665
P-Index
This Author published in this journals
All Journal ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika KLIK (Kumpulan jurnaL Ilmu Komputer) (e-Journal) Jurnal Teknologi dan Sistem Komputer International Journal of Artificial Intelligence Research Communications in Science and Technology SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan Elektrika Jurnal Abdi Insani Jurnal Pengabdian kepada Masyarakat Nusantara Bookchapter Pendidikan Universitas Negeri Semarang Indonesian Journal of Mathematics and Natural Sciences
Nugroho, Anan
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Medicine & Pharmacology Nursing Public Health Social Sciences Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Performance of Deep Face Recognition Models under Adaptive Margin Loss: A Real-Time Evaluation Aditama, Kevin Muhammad Tegar; Nugroho, Anan; Subiyanto, Subiyanto; Pongoh, Arthur Gregorius
International Journal of Artificial Intelligence Research Vol 9, No 1.1 (2025)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v9i1.1.1641

Abstract

Real-time face recognition systems encounter a critical trade-off between high-security demands and computational efficiency, particularly when deployed in unconstrained open-set environments. This study presents a comprehensive benchmarking of four distinct deep learning backbones ResNet100, GhostFaceNet, LAFS, and TransFace specifically trained using the Adaptive Margin Loss (AdaFace) function to handle image quality variations. The primary objective is to identify the optimal architecture for secure attendance systems operating on standard hardware with limited training data. The evaluation protocol employs a rigorous real-world open-set test to quantify performance using False Acceptance Rate (FAR) and False Rejection Rate (FRR). The experimental results demonstrate that ResNet100 establishes the highest security standard, achieving a 0.00% FAR at strict thresholds. Meanwhile, GhostFaceNet emerges as the most balanced solution for resource-constrained deployments, delivering competitive accuracy above 93% with significantly lower computational complexity. Conversely, the Vision Transformer (TransFace) fails to generalize in this low-data regime, resulting in unacceptable false acceptance rates. These findings definitively recommend GhostFaceNet for efficient edge-based implementations, while ResNet100 remains the superior choice for mission-critical security applications.
Co-Authors Abiaska, Arya Kresna Aditama, Kevin Muhammad Tegar Afifi, Sesaria Nisa Alamsyah - Alfa Faridh Suni Anggraini Mulwinda Arfriandi, Arief Ariolin, Anantha Revoislami Astagina, Paramesti Baehaqi Bambang Priyono Budi Sunarko Budiman, Kholiq Dwi Oktaviyanti, Dwi Firdaus, Agung Adi Ghulamzaki, Muhammad Hanung Adi Nugroho Hari Wibawanto Heny Setyawati Hidayatulloh, Dimas Restu Indaryanto, Faizal Lina Choridah Mahalul Azam Mubarak, Raihan Fa'iq Mukti, Gandhi Satria Noor Akhmad Setiawan Nurharsono, Tri Pongoh, Arthur Gregorius Pradana, Irzhafran Ridho Richardo, Hizkia Natanael Ricko Irawan Rismawan, Yudha Andriano Rizqi Fitri Naryanto Roni Saputra, Roni Rusiyanto Rusiyanto, Rusiyanto Said Sunardiyo Salsabila, Alif Mazida Savitri, Dina Wulung Septiani, Amalia Setiyawan, Farhan Taufikurrahman Setya Rahayu Soedjatmiko Soedjatmiko Sri Sukamta Tatyantoro Andrasto Ulfah Mediaty Arief Wafi, Ahmad Zein Al Wahyudi Wahyudi