Age Estimation Using AAM and Local Facial Features

  • Authors:
  • Jun-Da Txia;Chung-Lin Huang

  • Affiliations:
  • -;-

  • Venue:
  • IIH-MSP '09 Proceedings of the 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper proposes a new age estimation method by using Active Appearance Model(AAM) to extract the regions of age features. This method consists of four modules: detecting face, searching facial feature regions, finding age features, and age estimation. In the experiments, we demonstrate that the extracted age features can be applied to estimate age effectively. Using the portrait images of 200x240 pixels, the system recognition accuracy is about 73%.