Face Age Estimation Based on CSLBP and Lightweight Convolutional Neural Network

被引:0
作者
Wang, Yang [1 ]
Tian, Ying [1 ]
Tian, Ou [2 ]
机构
[1] Univ Sci & Technol Liaoning, Sch Comp Sci & Software Engn, Anshan 114051, Peoples R China
[2] Univ Wollongong, Med & Hlth Sci, Wollongong, NSW 2522, Australia
来源
CMC-COMPUTERS MATERIALS & CONTINUA | 2021年 / 69卷 / 02期
关键词
Face age estimation; lightweight convolutional neural network; CSLBP; SSR-Net;
D O I
10.32604/cmc.2021.018709
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:2203 / 2216
页数:14
相关论文
共 50 条
  • [11] Automatic classification of retinal diseases with transfer learning-based lightweight convolutional neural network
    Lu, Zhenzhen
    Miao, Jingpeng
    Dong, Jingran
    Zhu, Shuyuan
    Wang, Xiaobing
    Feng, Jihong
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 81
  • [12] Multi-classification Sensitive Image Detection Method Based on Lightweight Convolutional Neural Network
    Mao, Yueheng
    Song, Bin
    Zhang, Zhiyong
    Yang, Wenhou
    Lan, Yu
    KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2023, 17 (05): : 1433 - 1449
  • [13] Application Research of Bridge Damage Detection Based on the Improved Lightweight Convolutional Neural Network Model
    Du, Fujun
    Jiao, Shuangjian
    Chu, Kaili
    APPLIED SCIENCES-BASEL, 2022, 12 (12):
  • [14] A Lightweight Convolutional Neural Network for Ship Target Detection in SAR Images
    Hao, Yisheng
    Zhang, Ying
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2024, 60 (02) : 1882 - 1898
  • [15] A High Performance Reconfigurable Hardware Architecture for Lightweight Convolutional Neural Network
    An, Fubang
    Wang, Lingli
    Zhou, Xuegong
    ELECTRONICS, 2023, 12 (13)
  • [16] Image-based Concrete Cracks Identification under Complex Background with Lightweight Convolutional Neural Network
    Meng, Qingcheng
    Hu, Lei
    Wan, Da
    Li, Mingjian
    Wu, Haojie
    Qi, Xin
    Tian, Yongding
    KSCE JOURNAL OF CIVIL ENGINEERING, 2023, 27 (12) : 5231 - 5242
  • [17] Image-based Concrete Cracks Identification under Complex Background with Lightweight Convolutional Neural Network
    Qingcheng Meng
    Lei Hu
    Da Wan
    Mingjian Li
    Haojie Wu
    Xin Qi
    Yongding Tian
    KSCE Journal of Civil Engineering, 2023, 27 : 5231 - 5242
  • [18] A multi-feature fusion algorithm for driver fatigue detection based on a lightweight convolutional neural network
    Cheng, Wangfeng
    Wang, Xuanyao
    Mao, Bangguo
    VISUAL COMPUTER, 2024, 40 (04) : 2419 - 2441
  • [19] Research on Safety Detection of Transmission Line Disaster Prevention Based on Improved Lightweight Convolutional Neural Network
    Du, Fujun
    Jiao, Shuangjian
    Chu, Kaili
    MACHINES, 2022, 10 (07)
  • [20] A multi-feature fusion algorithm for driver fatigue detection based on a lightweight convolutional neural network
    Wangfeng Cheng
    Xuanyao Wang
    Bangguo Mao
    The Visual Computer, 2024, 40 : 2419 - 2441