Prediction of Gender and Age Period from Periorbital Region with VGG16

Year 2023, Volume: 5 Issue: 2, 105 - 110, 31.07.2023

Ömer Faruk Akmeşe , Hüseyin Çizmeci , Selim Özdem , Fikri Özdemir , Emre Deniz , Rabia Mazman , Murat Erdoğan , Esma Erdoğan

https://doi.org/10.51537/chaos.1257597

Abstract

Using deep learning methods, age and gender estimation from people’s facial area has become popular. Recently, with the increase in the use of masks due to Covid-19, only the eye area of people is seen. The periorbital region can give an idea about the person’s characteristics, such as age and gender. This study it is aimed to predict gender and age from images obtained by cutting the eye area from facial photographs of people using Visual Geometry Group-16 (VGG16). With the transfer learning method for age group (male, female) and gender group (child, youth, adults, and old) classification, 5714 images in the data set were used for the age group, and 3280 images were used for the gender group. As a result of this study, 99.41% success in age estimation and 95.73% in gender estimation was achieved.

Keywords

Deep learning, Age and Gender Prediction, VGG16, Periorbital area

References

• Abu Nada, A. M., E. Alajrami, A. A. Al-Saqqa, and S. S. Abu-Naser, 2020 Age and gender prediction and validation through single user images using cnn .
• Alkurdy, N. H., H. K. Aljobouri, and Z. K. Wadi, 2023 Ultrasound renal stone diagnosis based on convolutional neural network and vgg16 features. Int J Electr Comput Eng 13: 3440–3448.
• Aslan, M., 2022 Derin ö˘grenme tabanlı otomatik beyin tümör tespiti. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 34: 399– 407.
• Aslan, M. F., K. Sabanci, A. Durdu, and M. F. Unlersen, 2022 Covid- 19 diagnosis using state-of-the-art cnn architecture features and bayesian optimization. Computers in Biology and Medicine p. 105244.
• Bingol, K., A. E. Akan, H. T. Örmecio˘ glu, and A. Er, 2020 Artificial intelligence applications in earthquake resistant architectural design: Determination of irregular structural systems with deep learning and imageai method .
• Bulut, F., 2017 Örnek tabanlı sınıflandırıcı topluluklarıyla yeni bir klinik karar destek sistemi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi 32.
• Dilber, ˙I. and A. Çetin, 2021 Adli bili¸sim incelenme süreçlerinde yapay zeka kullanımı: Vgg16 ile görüntü sınıflandırma. Düzce Üniversitesi Bilim ve Teknoloji Dergisi 9: 1695–1706.
• Duan, M., K. Li, C. Yang, and K. Li, 2018 A hybrid deep learning cnn–elm for age and gender classification. Neurocomputing 275: 448–461.
• Generated Photos, 2022 AI Generated Photos. https://generated. photos/faces/datasets.
• Gündüz, G. and ˙I. H. Cedimo˘ glu, 2019 Derin ö˘grenme algoritmalarını kullanarak görüntüden cinsiyet tahmini. Sakarya University Journal of Computer and Information Sciences 2: 9–17.
• Hinton, G. E. and R. R. Salakhutdinov, 2006 Reducing the dimensionality of data with neural networks. science 313: 504–507.
• Kim, K. G., 2016 Book review: Deep learning. Healthcare informatics research 22: 351–354.
• Kumar, S., S. Singh, J. Kumar, and K. Prasad, 2022 Age and gender classification using seg-net based architecture and machine learning. Multimedia Tools and Applications 81: 42285–42308.
• Metlek, S. and K. Kayaalp, 2020 Derin ö˘grenme ve destek vektör makineleri ile görüntüden cinsiyet tahmini. Düzce Üniversitesi Bilim ve Teknoloji Dergisi 8: 2208–2228.
• Oladipo, O., E. O. Omidiora, and V. C. Osamor, 2022 A novel genetic-artificial neural network based age estimation system. Scientific Reports 12: 19290.
• ¸Seker, A., B. Diri, and H. H. Balık, 2017 Derin ö˘grenme yöntemleri ve uygulamaları hakkında bir inceleme. Gazi Mühendislik Bilimleri Dergisi 3: 47–64.
• Solmaz, R., A. ALKAN, and M. GÜNAY, 2020 Mobile diagnosis of thyroid based on ensemble classifier. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi 11: 915–924.
• Theckedath, D. and R. Sedamkar, 2020 Detecting affect states using vgg16, resnet50 and se-resnet50 networks. SN Computer Science 1: 1–7.
• Zha, W., Y. Liu, Y. Wan, R. Luo, D. Li, et al., 2022 Forecasting monthly gas field production based on the cnn-lstm model. Energy p. 124889.
• Zhu, F., J. Li, B. Zhu, H. Li, and G. Liu, 2023 Uav remote sensing image stitching via improved vgg16 siamese feature extraction network. Expert Systems with Applications p. 120525.