TR
EN
PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET
Abstract
With the developing technology, smart systems have started to take place in our daily lives. Accordingly, it is very important for the systems that will actively participate in social life to adapt to social life properly. One of the most important steps of adapting to social life is communication. Facial expressions are one of the most important parts of communication that usually supports verbal communication. For this reason, many studies have been carried out on identifying facial expressions. The vast majority of these studies were carried out using datasets containing only adult faces. Conducting studies that do not involve the elderly and children may lead to the creation and development of highly biased smart systems. Therefore, this article focuses on detecting children's facial expressions. In order to detect facial expressions in children, a data set was prepared with images collected from search engines using keywords. By using the transfer learning method, the success of VGG16, ResNet50, DenseNet121, InceptionV3, InceptionResNetV2 and Xception models were evaluated and compared on this prepared data set. According to the evaluation results, the best result was obtained with the InceptionV3 model with an accuracy rate of 76.3% and an F1 score of 0.76.
Keywords
Kaynakça
- Jack R.E., Schyns P.G. The Human Face as a Dynamic Tool for Social Communication. Curr Biol. 2015; 25:R621–R634. https://doi.org/10.1016/j.cub.2015.05.052.
- DeVito Jospeh A. Human Communication. Boston: Pearson; 2002.
- Howard A., Zhang C., Horvitz E. Addressing bias in machine learning algorithms: A pilot study on emotion recognition for intelligent systems. 2017 IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO 2017. Austin, TX, USA; 2017. https://doi.org/10.1109/ARSO.2017.8025197.
- Guo G., Guo R., Li X. Facial expression recognition influenced by human aging. IEEE Trans. Affect. Comput. 2013; 4: 291–298. https://doi.org/10.1109/T-AFFC.2013.13.
- Houstis O., Kiliaridis S. Gender and age differences in facial expressions. Eur. J. Orthod. 2009; 31: 459–466. https://doi.org/10.1093/ejo/cjp019.
- Brandao M., Age and gender bias in pedestrian detection algorithms. arXiv Prepr. arXiv:1906.10490, 2019.
- Egger H.L., Pine D.S., Nelson E., Leibenluft E., Ernst M., Towbin, K.E., et al. The NIMH Child Emotional Faces Picture Set (NIMH-ChEFS): a new set of children’s facial emotion stimuli. Int. J. Methods Psychiatr. Res. 2011; 20: 145–156. https://doi.org/10.1002/mpr.343.
- Lobue V., Thrasher C., Kret M.E. The Child Affective Facial Expression (CAFE) set: validity and reliability from untrained adults. Front. Psychol. 2015; 5: 1532. https://doi.org/10.3389/fpsyg.2014.01532.
Ayrıntılar
Birincil Dil
İngilizce
Konular
Mühendislik
Bölüm
Araştırma Makalesi
Yayımlanma Tarihi
27 Mart 2023
Gönderilme Tarihi
12 Kasım 2021
Kabul Tarihi
4 Ocak 2023
Yayımlandığı Sayı
Yıl 2023 Cilt: 12 Sayı: 1
APA
Sayın, İ., & Aksoy, B. (2023). PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET. Türk Doğa ve Fen Dergisi, 12(1), 12-20. https://doi.org/10.46810/tdfd.1022507
AMA
1.Sayın İ, Aksoy B. PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET. TDFD. 2023;12(1):12-20. doi:10.46810/tdfd.1022507
Chicago
Sayın, İrem, ve Bekir Aksoy. 2023. “PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET”. Türk Doğa ve Fen Dergisi 12 (1): 12-20. https://doi.org/10.46810/tdfd.1022507.
EndNote
Sayın İ, Aksoy B (01 Mart 2023) PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET. Türk Doğa ve Fen Dergisi 12 1 12–20.
IEEE
[1]İ. Sayın ve B. Aksoy, “PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET”, TDFD, c. 12, sy 1, ss. 12–20, Mar. 2023, doi: 10.46810/tdfd.1022507.
ISNAD
Sayın, İrem - Aksoy, Bekir. “PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET”. Türk Doğa ve Fen Dergisi 12/1 (01 Mart 2023): 12-20. https://doi.org/10.46810/tdfd.1022507.
JAMA
1.Sayın İ, Aksoy B. PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET. TDFD. 2023;12:12–20.
MLA
Sayın, İrem, ve Bekir Aksoy. “PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET”. Türk Doğa ve Fen Dergisi, c. 12, sy 1, Mart 2023, ss. 12-20, doi:10.46810/tdfd.1022507.
Vancouver
1.İrem Sayın, Bekir Aksoy. PROPOSAL OF NEW DATASET FOR CHILD FACE EXPRESSION RECOGNITION AND COMPARISON OF DEEP LEARNING MODELS ON THE PROPOSED DATASET. TDFD. 01 Mart 2023;12(1):12-20. doi:10.46810/tdfd.1022507