Title:	Sex Classification of Face Images using Embedded Prototype Subspace Classifiers
Authors:	Hast, Anders
Citation:	WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vis 43-52.ion, p.
Issue Date:	2023
Publisher:	Václav Skala - UNION Agency
Document type:	konferenční příspěvek conferenceObject
URI:	http://hdl.handle.net/11025/54398
ISBN:	978-80-86943-32-9
ISSN:	2464–4617 (print) 2464–4625 (CD/DVD)
Keywords:	pohlaví a klasifikace pohlaví;klasifikace podprostoru vloženého prototypu;subprostor;rozpoznávání obličejů
Keywords in different language:	sex and gender classification;subspaces;Embedded Prototype Subspace Classification;face recognition
Abstract in different language:	In recent academic literature Sex and Gender have both become synonyms, even though distinct definitions do exist. This give rise to the question, which of those two are actually face image classifiers identifying? It will be argued and explained why CNN based classifiers will generally identify gender, while feeding face recognition feature vectors into a neural network, will tend to verify sex rather than gender. It is shown for the first time how state of the art Sex Classification can be performed using Embedded Prototype Subspace Classifiers (EPSC) and also how the projection depth can be learned efficiently. The automatic Gender classification, which is produced by the InsightFace project, is used as a baseline and compared to the results given by the EPSC, which takes the feature vectors produced by InsightFace as input. It turns out that the depth of projection needed is much larger for these face feature vectors than for an example classifying on MNIST or similar. Therefore, one important contribution is a simple method to determine the optimal depth for any kind of data. Furthermore, it is shown how the weights in the final layer can be set in order to make the choice of depth stable and independent of the kind of learning data. The resulting EPSC is extremely light weight and yet very accurate, reaching over 98% accuracy for several datasets.
Rights:	© Václav Skala - UNION Agency
Appears in Collections:	WSCG 2023: Full Papers Proceedings

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.