Abstract—The age is one of the most important features of a human being, and its estimation is essential in many applications, such as security control and surveillance monitoring. This work presents a framework for facial age estimation based on ensemble of individual age estimators. Both mathematical and experimental proofs show, if the individual age estimators are diverse in error, then to improve the results, we can make the ensemble age estimator using the best selected individual age estimators. We emphasize that although the experiments presented here are performed by neural networks, the proposed framework is readily applicable to any other regressor.
Index Terms—AAge estimation, ensemble technique, facial images, neural networks.
A. K. Choobeh is with the Young Researchers Club, Buinzahra Branch, Islamic Azad University, Buinzahra, Iran (e-mail: keshavarz_c@ yahoo.com).
Cite: Alireza Keshavarz Choobeh, "Improving Automatic Age Estimation Algorithms using an Efficient Ensemble Technique," International Journal of Machine Learning and Computing vol. 2, no. 2, pp. 118-122, 2012.