<![CDATA[The main objective of this study was to develop a method for estimating theage and gender of a person based on facial images, using CNN in-depthtraining that can accurately recognize age and gender. Information that isextracted can be useful in, for example, security or commercial applications.This is a difficult estimation problem, because the only information we have isa picture, that is the look of that person.The next aspect of this study I focused on incorporating architecture for ageand gender recognition to take advantage of gender-specific agecharacteristics and age-specific gender characteristics inherent in the image.This comes from the observation that sex classifications are tasks that areinherently easier than age classifications, because both fewer and fewerpotential classes and more prominent intra-gender facial variations. With thetraining of different age classifiers for each gender I found that I could improvethe performance of age classifications, even though gender classification didnot see significant results.]]>
Copyrights © 2020
