Open Access Open Access  Restricted Access Subscription Access

Challenging Aspects for Facial Feature Extraction and Age Estimation


Affiliations
1 Computer Science and Engineering, Sathyabama University, Chennai – 600119, Tamil Nadu, India
 

In this paper we have discussed the steps for facial age estimation and a comparative study of various methodologies in each step has been briefed. The face identification, tools for extraction, feature normalization, features to be extracted is all explained. In spite of various challenges, feature extraction is a vital step based on which the classification and estimation of age are done. From the comparative study DCT method has provided better results across all age groups.

Keywords

DCT (Discrete Cosine Transform), HMM (Hidden Markov Models), LBP (Local Binary Pattern), MAE (Mean Absolute Error), PCA (Principle Component Analysis)
User

Abstract Views: 217

PDF Views: 0




  • Challenging Aspects for Facial Feature Extraction and Age Estimation

Abstract Views: 217  |  PDF Views: 0

Authors

A. Deepa
Computer Science and Engineering, Sathyabama University, Chennai – 600119, Tamil Nadu, India
T. Sasipraba
Computer Science and Engineering, Sathyabama University, Chennai – 600119, Tamil Nadu, India

Abstract


In this paper we have discussed the steps for facial age estimation and a comparative study of various methodologies in each step has been briefed. The face identification, tools for extraction, feature normalization, features to be extracted is all explained. In spite of various challenges, feature extraction is a vital step based on which the classification and estimation of age are done. From the comparative study DCT method has provided better results across all age groups.

Keywords


DCT (Discrete Cosine Transform), HMM (Hidden Markov Models), LBP (Local Binary Pattern), MAE (Mean Absolute Error), PCA (Principle Component Analysis)



DOI: https://doi.org/10.17485/ijst%2F2016%2Fv9i4%2F130322