Sakarya University Journal of Computer and Information Sciences
Yazarlar: Gül GÜNDÜZ, İsmail Hakkı CEDİMOĞLU
Konular:Mühendislik
DOI:10.35377/saucis.02.01.517930
Anahtar Kelimeler:Deep Learning,Deep learning algorithms,Gender estimation
Özet: In our age, where big data is processed at great speeds, deep learning algorithms are used to facilitate the solution of various problems by extracting different parameters from billions of data. In this study, it is aimed to determine the genders of female, male, old, young, child and baby photographs in the existing data sets with deep learning algorithms. To realize this prediction algorithm, various deep learning libraries were used and a new model with deep learning models Alex Net and VGG-16 was compared. The data set used in the application is composed of male and female images. Each image is labeled according to the gender and age of the person. This data set includes 3170 training data and 318 test data. The results of three different models were compared. The article explains in detail how to make a gender prediction using deep learning algorithms and aims to contribute to the literature studies.
Dergi editörleri editör girişini kullanarak sisteme giriş yapabilirler. Editör girişi için tıklayınız.