Compound Stratum Practice

Abstract

A person’s face provides a lot of information such as age, gender and identity.  Faces play an important role in the estimation and prediction of the age and gender of persons, just by looking at their face.  Perceiving human faces and modeling the distinctive features of human faces that contribute most towards face recognition are some of the challenges faced by computer vision and psychophysics researchers.  There  are  many methods  have  been  proposed  in  the  literature for  the  facial features for age and gender classification.

In this book, an attempt is made to classify human age and gender using feed forward propagation Neural Networks in Coarser level.  Further final classification is done using 3-sigma control limits in Compound level.  Proposed approach efficiently classifies three age groups including Children, Middle-aged adults and Old aged adults.  Similarly, two gender groups classified into Male and Female by the proposed Compound Stratum method.

The performance of the system is further improved by employing Compound Stratum Practice using 3 Sigma Control Limits applied on the output of the Artificial Neural Network classifier.  The Mean and Standard Deviation has been considered on the output generated from the Neural Network classifier, and 3 sigma control limits has been applied to define the range of values for the specific category of age and gender.  The efficiency of the system is demonstrated through the experimental results using benchmark database images.