MULTI-ARCHITECTURE DEEP LEARNING FOR SUBJECT INDEPENDENT FACIAL EXPRESSION RECOGNITION
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) · 28.05.2026 · 11 (4) · 1293-1305
DOI: 10.33480/jitk.v11i4.7404 ↗Kurz gefasst
Fachartikel in der Zeitschrift JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), online erschienen am 28.05.2026. Verfasst von Taufiq und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Facial Expression Recognition (FER) remains a challenging problem in computer vision, particularly under subject-independent conditions in which models must generalize to individuals not seen during training. This study reports a controlled comparative evaluation of three Convolutional Neural Network (CNN) architectures — MobileNetV3-Large, EfficientNet-B3, and ResNet50 — using the Extended Cohn-Kanade (CK+) dataset (981 apex-frame images, 118 subjects, seven emotion classes). All models were trained and tested under identical experimental conditions with a subject-disjoint partition (72/23/23 subjects for training, validation, and testing), so that observed performance differences may be attributed primarily to architectural design. The results indicate that MobileNetV3-Large attains the highest test accuracy of 95.16%, exceeding EfficientNet-B3 (93.01%) and ResNet50 (91.94%), while requiring the fewest parameters (~5.4M) and the shortest inference latency (~8.2 ms per image). A multi-dimensional evaluation covering per-class metrics and computational cost is also reported. These observations provide preliminary architectural guidance for FER deployment in resource-constrained environments; however, because they are derived from a single dataset and a single subject split, broader claims should be confirmed on more diverse benchmarks.
Zitieren
APA
Taufiq, Muhammad, Asran, Ezwarsyah, & Muthalib, M. A. (2026). MULTI-ARCHITECTURE DEEP LEARNING FOR SUBJECT INDEPENDENT FACIAL EXPRESSION RECOGNITION. JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), 11(4), 1293-1305. https://doi.org/10.33480/jitk.v11i4.7404
Vancouver
Taufiq, Muhammad, Asran, Ezwarsyah, Muthalib MA. MULTI-ARCHITECTURE DEEP LEARNING FOR SUBJECT INDEPENDENT FACIAL EXPRESSION RECOGNITION. JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer). 2026;11(4):1293-1305. doi:10.33480/jitk.v11i4.7404
BibTeX
@article{Taufiq2026,
author = {Taufiq and Muhammad and Asran and Ezwarsyah and Muthalib, Muchlis Abdul},
title = {MULTI-ARCHITECTURE DEEP LEARNING FOR SUBJECT INDEPENDENT FACIAL EXPRESSION RECOGNITION},
journal = {JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer)},
year = {2026},
volume = {11},
number = {4},
pages = {1293--1305},
doi = {10.33480/jitk.v11i4.7404}
}
EUVIMED