An Unsupervised Neural Network Method for Age Group Estimation using Facial Features
Matthias Omotayo Oladele, Elijah Olusayo Omidiora · Transactions on Machine Learning and Artificial Intelligence · 2015
Age estimation from facial features is an important research subject in the field of face recognition. It is an active research area that can be used in wide range of applications such as surveillance and security, telecommunication and digital libraries, human-computer intelligent interaction, and smart environment. This paper developed an unsupervised neural network by using a Self – Organizing Feature Map (SOFM) to estimate age group from facial features.The face images were divided into eight different age groups ranging from babies, young teenagers, mid teenagers, teenagers, young adults, mid adults, young old and old and SOFM was used to estimate the age group from the input face image. Principal Component Analysis (PCA) was used to extract the facial features and the extracted features were presented to the SOFM for training and testing. The developed system was experimented with 630 face images with different ages from the FG-NET database. 450 samples were used for training while 180 were used for testing. The results showed a training time of 116.333 seconds and an accuracy of 92.2%.