An amalgamation of active appearance model and opponent color local binary pattern in age estimation

Citation

Chang, Quan Yan and Chong, Siew Chin and Ong, Thian Song (2022) An amalgamation of active appearance model and opponent color local binary pattern in age estimation. Journal of Engineering Science and Technology., 17 (6). pp. 4130-4143. ISSN 1823-4690

[img] Text
17_6_28.pdf - Published Version
Restricted to Repository staff only

Download (523kB)

Abstract

Facial images are broadly used in differentiating various types of personality traits including age recognition. Age estimation is used to determine a person’s age based on their biometric feature characteristics. In this proposed work, age estimation is evaluated by extracting the important features of the facial appearance. This paper presents two ways of age estimation implementations, namely Two-Step Implementation and Score-Level Implementation by utilizing the methods of Active Appearance Model (AAM) and Opponents-Color Local Binary Pattern (OCLBP). In both implementations, the weaknesses of AAM and OCLBP are minimized and the strengths of both are used to complement each other for a better age estimation model. The benchmarked age estimation datasets have been used to evaluate the proposed implementation method with promising results generated. © School of Engineering, Taylor’s University.

Item Type: Article
Uncontrolled Keywords: Active appearance model, Age estimation, Face recognition Local binary
Subjects: Q Science > QC Physics > QC350-467 Optics. Light
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 16 Mar 2023 01:40
Last Modified: 16 Mar 2023 01:40
URII: http://shdl.mmu.edu.my/id/eprint/11248

Downloads

Downloads per month over past year

View ItemEdit (login required)