期刊名称：International Journal of Electronics Communication and Computer Technology
印刷版ISSN：2249-7838
出版年度：2015
卷号：5
期号：Special
出版社：International Journal of Electronics Communication and Computer Technology
摘要：A person's face provides a lot of information such as age, gender and identity. Faces plays an important role in the estimation/prediction of the age of persons, just by looking at their face. In this research, an attempt is made to design a model to classify human age according to features extracted from human facial images using Neural Network (NN). Now a days, Artificial Neural Network (ANN) has been widely used as a tool for solving many decision modeling problems. In this paper a feed forward propagation neural networks are constructed for age group classification system for gray-scale facial images. Three age groups including Children, Middle-aged adults and Old adults are used in the classification system. The age of the facial images of Babies/Children ranges from 1 to 16. The age of the facial images of the Middle-aged persons ranges fro m 16 to 60. The age of the Old-aged persons is considered as 60 and above. In this paper, a second level decision ha s been proposed in w hich the output obtained from the N eural Network(Primary Level) has been refined at the Second level in order to improvise the accuracy of the detection rate. The accuracy of the system is analyzed by the variation on the range of the age groups. The efficiency of the system is demonstrated through the experimental results.
