Age prediction on face features via multiple classifiers

Mohamad, F.S. and Iqtait, M. and Alsuhimat, F. (2018) Age prediction on face features via multiple classifiers. In: 4th International Conference on Computer and Technology Applications, ICCTA 2018, 03-05 May 2018, Istanbul, Turkey.

[img] Image
FH03-FIK-18-14464.jpg
Restricted to Registered users only

Download (144kB)

Abstract

Human age recognition becomes increasingly important due to its beneficial employments alongside security and computer applications. Age prediction from face picture has a lot of challenges, such as insufficiency of training data and uncontrollable situation. In this research, we address these critical issues by introducing an improved age prediction algorithm using Active Appearance Models (AAM) and three classifiers, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Support Vector Regression (SVR) to improve the precision of age prediction based on the present methods. In this algorithm, the traits of the facial pictures are explicated as traits vectors by AAM model, and the classifiers are utilized to estimate the age. We were able to recognize that the accuracy of SVR algorithm is better than the accuracy of KNN and SVM classifiers.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Active Appearance Models (AAM), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Support Vector Regression (SVR)
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Informatics & Computing
Depositing User: Muhammad Akmal Azhar
Date Deposited: 19 Nov 2020 06:24
Last Modified: 19 Nov 2020 06:24
URI: http://eprints.unisza.edu.my/id/eprint/1667

Actions (login required)

View Item View Item