Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
In a world relying ever more on human classification, this papers aims to improve on age and gender image classification through the use of Convolutional Neural Networks (CNN). Age and gender classification has become a popular area of study in the past number of years however there are still improvements to be made, particularly in the area of age classification. This research paper aims to test the currently accepted fact that CNN models are the superior model type for image classification by comparing CNN performance against Support Vector Machine performance on the same dataset. Using the Adience image classification dataset, this research also focuses on the implementation of data augmentation techniques, some more novel than others, as a means of improving CNN performance. In terms of standard popular methods of augmentation, image mirroring and image rotation were applied. As well as these, a more novel approach to augmentation was applied to the area of age classification. This technique was completed using Faceapp, an AI image editor in the form of a mobile application. This application allows for the placement of ”filters” on images of human beings in order to alter their appearance. The results of the data augmented models were superior to that of the standard CNN models with gender classification improving by 2.6% while age classification improved by 7.1%. The results of this research establish the potential for further improvements through the inclusion of more augmentation techniques or through the use of more filter types provided in the Faceapp application.
Kelliher, E. (2021). Human Age and Gender Classification using Convolutional Neural Networks. Technological University Dublin. DOI: 10.21427/VBE0-WX80