jip.4.3.13921
Age Prediction Using Facial Images
Reshma Zabeen K.T.
V. Savithri
Journal on Image Processing
2349-6827
4
3
16
21
jip.4.3.13921
Age Group Identification, Active Appearace Model (AAM), Wrinkle Analysis, Facial Landmark Points, Mean Classification Algorithm
Age estimation plays a vital role in human computer interaction where the image is given as input to the system after which, with the applied techniques the system provides result. An age group prediction system is estimated through AAM (Active Appearance Model) which calculates the texture and shape. A wrinkle is identified as a part of the shape information and the features, such as eye, nose, chin, lip, cheeks are extracted using PCA (Principle Component Analysis) of AAM, which then calculates the distance between the features and are stored as facial landmark points. The points are fed as input to the Mean Classification Algorithm which classifies based on two age groups, adult and old. Finally the Mean Absolute Error (MAE) value is estimated to determine the accuracy.
July - September 2017
Copyright © 2017 i-manager publications. All rights reserved.
i-manager Publications
http://www.imanagerpublications.com/Article.aspx?ArticleId=13921