Klasifikasi Dan Pengenalan Pola Pada Citra Wajah Anak
DOI:
https://doi.org/10.29407/1ch1pe42Keywords:
Convolutional Neural Network, emosi anak, pengolahan citra digitalAbstract
Emosi anak memiliki peran penting dalam mendukung proses pembelajaran dan perkembangan psikologis, namun identifikasinya masih sering dilakukan secara subjektif dan kurang akurat. Penelitian ini bertujuan untuk mengkaji bagaimana pengolahan citra digital dan implementasi algoritma Convolutional Neural Network (CNN) dapat digunakan untuk mengidentifikasi emosi pada citra wajah anak. Penelitian ini menggunakan pendekatan kualitatif deskriptif dengan data berupa citra wajah anak yang diambil secara alami selama kegiatan pembelajaran di kelas. Tahapan penelitian meliputi pengumpulan data citra, pra-pemrosesan yang mencakup deteksi wajah dan normalisasi citra, serta proses klasifikasi menggunakan CNN. Algoritma CNN bekerja dengan mengekstraksi fitur penting wajah melalui lapisan konvolusi dan pooling, kemudian melakukan klasifikasi emosi pada lapisan fully connected. Sistem mengklasifikasikan ekspresi wajah ke dalam empat kategori emosi, yaitu senang, sedih, marah, dan netral. Hasil penelitian menunjukkan bahwa CNN mampu mengidentifikasi emosi wajah anak dengan baik, terutama pada emosi senang dan marah. Meskipun masih terdapat keterbatasan akibat variasi pencahayaan dan sudut pengambilan gambar, sistem ini berpotensi menjadi alat bantu objektif dalam memahami kondisi emosional anak untuk mendukung proses pembelajaran yang lebih adaptif..
Downloads
References
[[1] S. A. Denham, K. Bassett, and E. Wyatt, “The socialization of emotional competence in early childhood,” Handbook of Emotional Development, vol. 2, no. 1, pp. 45–67, 2020.
[2] L. A. Camras and M. M. Shuster, “Understanding emotion expression in children: Challenges and implications,” Developmental Psychology, vol. 58, no. 4, pp. 721–734, 2022.
[3] Y. Li and H. Zhang, “Facial expression recognition based on machine learning techniques: A review,” Journal of Visual Communication and Image Representation, vol. 78, pp. 103–115, 2021.
[4] N. Sari, A. Pratama, and R. Hidayat, “Emotion recognition system for early detection of children’s emotional disorders,” International Journal of Educational Technology, vol. 10, no. 2, pp. 89–98, 2023.
[5] A. Kumar, R. Singh, and P. Gupta, “Deep learning approaches for facial emotion recognition: A comparative study,” IEEE Access, vol. 10, pp. 45678–45690, 2022.
[6] M. Rahman, S. Islam, and T. Rahman, “Challenges in facial expression recognition of children under unconstrained environments,” Proceedings of the International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 112–118, 2021.
[7] J. Zhao, L. Wang, and Y. Chen, “Artificial intelligence-based emotion recognition systems for educational applications,” IEEE Transactions on Affective Computing, vol. 15, no. 1, pp. 25–38, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Desitryani Seran, Virginia Abuk Klau, Elisabeth Dahu Seran
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
