IMPROVING CNN FEATURES FOR FACIAL EXPRESSION RECOGNITION
ZERO: Jurnal Sains, Matematika dan Terapan · 2019
DOI: 10.30829/zero.v3i1.5881 ↗Kurz gefasst
Fachartikel in der Zeitschrift ZERO: Jurnal Sains, Matematika dan Terapan, 2019. Verfasst von Ahmet Serdar Karadeniz und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Facial expression recognition is one of the challenging tasks in computer
vision. In this paper, we analyzed and improved the performances both
handcrafted features and deep features extracted by Convolutional Neural
Network (CNN). Eigenfaces, HOG, Dense-SIFT were used as handcrafted features.
Additionally, we developed features based on the distances between facial
landmarks and SIFT descriptors around the centroids of the facial landmarks,
leading to a better performance than Dense-SIFT. We achieved 68.34 % accuracy
with a CNN model trained from scratch. By combining CNN features with
handcrafted features, we achieved 69.54 % test accuracy.
Key Word: Neural network, facial expression recognition, handcrafted features
Zitieren
APA
Karadeniz, A. S., Karadeniz, M. F., Weber, G. W., & Husein, I. (2019). IMPROVING CNN FEATURES FOR FACIAL EXPRESSION RECOGNITION. ZERO: Jurnal Sains, Matematika dan Terapan. https://doi.org/10.30829/zero.v3i1.5881
Vancouver
Karadeniz AS, Karadeniz MF, Weber GW, Husein I. IMPROVING CNN FEATURES FOR FACIAL EXPRESSION RECOGNITION. ZERO: Jurnal Sains, Matematika dan Terapan. 2019. doi:10.30829/zero.v3i1.5881
BibTeX
@article{Karadeniz2019,
author = {Karadeniz, Ahmet Serdar and Karadeniz, Mehmet Fatih and Weber, Gerhard Wilhelm and Husein, Ismail},
title = {IMPROVING CNN FEATURES FOR FACIAL EXPRESSION RECOGNITION},
journal = {ZERO: Jurnal Sains, Matematika dan Terapan},
year = {2019},
doi = {10.30829/zero.v3i1.5881}
}
EUVIMED