EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Facial Emotion Recognition via Fusion of Deep and Handcrafted Features

Seo Eun Cha, Beom Kwon iD

Sensors · 16.07.2026 · 26 (14) · 4522

DOI: 10.3390/s26144522 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 16.07.2026. Verfasst von Seo Eun Cha und 1 weiteren Autor:innen. Beteiligte Einrichtung: Division of Information Science, Dongduk Women's University, Seoul 02784, Republic of Korea. Hauptthemen laut MEDLINE: Emotions, Facial Expression, Face. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dongduk Women's University, Dongduk Women’s University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Facial emotion recognition plays an important role in affective computing and human–computer interaction. Although convolutional neural network (CNN)-based methods have demonstrated remarkable performance, deep features alone may not sufficiently capture subtle geometric deformations and local texture variations, particularly under limited training data and challenging real-world conditions. To address this limitation, this study proposes a hybrid framework that integrates CNN-based deep features with handcrafted geometric and texture features. Specifically, 17 landmark-based angular features extracted from the eyebrows, eyes, nose, and mouth are combined with histogram of oriented gradients (HOG) features extracted from the nose and mouth regions through feature-level concatenation. The proposed method was extensively evaluated on three controlled datasets (JAFFE, CK+, and KDEF) and two large-scale in-the-wild datasets (RAF-DB and AffectNet). Five-fold cross-validation, leave-one-subject-out cross-validation, statistical significance analysis using paired t-tests, computational efficiency analysis, and comparisons with conventional handcrafted methods, standard CNN models, transfer learning-based methods, and recent hybrid feature-fusion methods were performed to comprehensively validate the proposed approach. Experimental results demonstrated consistent improvements across different datasets, evaluation protocols, and CNN backbone networks while maintaining a favorable balance between recognition performance and computational efficiency. These findings demonstrate that handcrafted geometric and local texture features effectively complement CNN-based deep representations, providing a robust and generalizable framework for facial emotion recognition across both controlled and large-scale in-the-wild datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmotionsFacial ExpressionFaceHumansConvolutional Neural NetworksAlgorithmsNeural Networks, Computer

Stichwörter der Autor:innen

convolutional neural networkdeep featurefacial emotion recognitionfacial landmarksfeature fusionhandcrafted featureshistogram of oriented gradients

Autor:innen und Institutionen

  • Division of Information Science, Dongduk Women's University, Seoul 02784, Republic of Korea.
  • Division of Interdisciplinary Studies in Cultural Intelligence, Dongduk Women's University, Seoul 02748, Republic of Korea.

ORCID-Profile: Beom Kwon

Förderung

  • Dongduk Women's University
  • Dongduk Women’s University

Zitieren

APA

Cha, S. E., & Kwon, B. (2026). Facial Emotion Recognition via Fusion of Deep and Handcrafted Features. Sensors, 26(14), 4522. https://doi.org/10.3390/s26144522

Vancouver

Cha SE, Kwon B. Facial Emotion Recognition via Fusion of Deep and Handcrafted Features. Sensors. 2026;26(14):4522. doi:10.3390/s26144522

BibTeX
@article{Cha2026,
  author = {Cha, Seo Eun and Kwon, Beom},
  title = {Facial Emotion Recognition via Fusion of Deep and Handcrafted Features},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4522},
  doi = {10.3390/s26144522}
}
Kostenlos starten →