Open Access

ARTICLE

Face Age Estimation Based on CSLBP and Lightweight Convolutional Neural Network

Yang Wang¹, Ying Tian^1,*, Ou Tian²

1 School of Computer Science and Software Engineering, University of Science & Technology Liaoning, Anshan, 114051, China
2 Medical and Health Sciences, University of Wollongong, NSW, 2522, Australia

* Corresponding Author: Ying Tian. Email:

Computers, Materials & Continua 2021, 69(2), 2203-2216. https://doi.org/10.32604/cmc.2021.018709

Received 17 March 2021; Accepted 18 April 2021; Issue published 21 July 2021

Abstract

As the use of facial attributes continues to expand, research into facial age estimation is also developing. Because face images are easily affected by factors including illumination and occlusion, the age estimation of faces is a challenging process. This paper proposes a face age estimation algorithm based on lightweight convolutional neural network in view of the complexity of the environment and the limitations of device computing ability. Improving face age estimation based on Soft Stagewise Regression Network (SSR-Net) and facial images, this paper employs the Center Symmetric Local Binary Pattern (CSLBP) method to obtain the feature image and then combines the face image and the feature image as network input data. Adding feature images to the convolutional neural network can improve the accuracy as well as increase the network model robustness. The experimental results on IMDB-WIKI and MORPH 2 datasets show that the lightweight convolutional neural network method proposed in this paper reduces model complexity and increases the accuracy of face age estimations.

---

Keywords

---