A novel genetic-artificial neural network based age estimation system

Oluwasegun Oladipo; Elijah Olusayo Omidiora; Victor Chukwudi Osamor

doi:10.1038/s41598-022-23242-5

A novel genetic-artificial neural network based age estimation system

Sci Rep. 2022 Nov 11;12(1):19290. doi: 10.1038/s41598-022-23242-5.

Authors

Oluwasegun Oladipo¹, Elijah Olusayo Omidiora², Victor Chukwudi Osamor³

Affiliations

¹ Department of Computer and Information Sciences, Covenant University, Ota, Ogun State, Nigeria.
² Department of Computer Science and Engineering, Ladoke Akintola University of Technology (LAUTECH), Ogbomoso, Oyo State, Nigeria.
³ Department of Computer and Information Sciences, Covenant University, Ota, Ogun State, Nigeria. vcosamor@gmail.com.

Abstract

Age estimation is the ability to predict the age of an individual based on facial clues. This could be put to practical use in underage voting detection, underage driving detection, and overage sportsmen detection. To date, no popular automatic age estimation system has been developed to target black faces. This study developed a novel age estimation system from the combination of a genetic algorithm and a back propagation (BP)-trained artificial neural network (ANN) and using the local binary pattern feature extraction technique (LBGANN) targeted at black faces. The system was trained with a predominantly black face database, and the result was compared against that of a standard ANN system (LBANN). The results showed that the developed system LBGANN outperformed the LBANN in terms of the correct classification rate.

MeSH terms

Algorithms*
Neural Networks, Computer*