Gender recognition from face images based on convolutional neural network (CNN)

Harry Yuliansyah; Lutfi Arazi

doi:10.1063/5.0130061

← Back to search

Gender recognition from face images based on convolutional neural network (CNN)

Closed

Harry Yuliansyah, Lutfi Arazi

2023 AIP Conference Proceedings Vol. 2623 Issue 1 Conference paper Cited by 0 SDG 5

Abstract

Human face images store much information, where the face is a multidimensional visual model of humans that can show identity such as gender. This paper proposes gender recognition from face images based on a convolutional neural network (CNN). The dataset source was obtained from the Kaggle website, Github, and the acquisition itself using a mobile phone camera. The total number of datasets used in this project is 6856 images divided into three parts: training, validation, and test. There are two classes used, namely the female and male classes. The CNN model is designed using five convolution layers for the feature extraction part. Several optimizations were made to the parameters of the number of epochs, learning rate, and batch size to get the best performance. The CNN model achieved a performance rate of 97%. © 2023 Author(s).

Affiliations

Electrical Engineering Department, Institut Teknologi Sumatera, Lampung Selatan, Indonesia

View full text (DOI) →

Research at a Glance

Research at a Glance

Topics & SDG Alignment

Collaboration

Author Profile (Selected)

References Overview

Journal & Source

Metadata & Integrity