The Video-Based Age and Gender Recognition with Convolution Neural Networks

P. 37–46.

Savchenko A., Kharchevnikova Angelina S.

The paper reviews the problem of age and gender recognition methods for video data using modern deep convolutional neural networks. We present the comparative analysis of classifier fusion algorithms to aggregate decisions for individual frames. We implemented the video-based recognition system with several aggregation methods to improve the age and gender identification accuracy. The experimental comparison of the proposed approach with traditional simple voting using IJB-A, Indian Movies, and Kinect datasets is provided. It is demonstrated that the most accurate decisions are obtained using the geometric mean and mathematical expectation of the outputs at softmax layers of the convolutional neural networks for gender recognition and age prediction, respectively.

Keywords: мобильные приложения, mobile applications, convolutional neural networks, age and gender recognition, сверточные нейронные сети, распознавание пола и возраста

Publication based on the results of: Разработка и апробация эффективных методов классификации для больших баз мультимедийных данных (2017)

In book

Computational Aspects and Applications in Large-Scale Networks. Springer Proceedings in Mathematics & Statistics

Valery A. Kalyagin, Panos M. Pardalos, Oleg Prokopyev, Irina Utkina Vol. 247. , Springer, 2018.