Comparison of Face Recognition Neural Networks
Name
Zepp Uibo
Abstract
The goal of this work was to compare three face recognition neural networks that had been
recently published. All of those networks had shown good results on a benchmark containing
mostly higher quality images of celebrities. The interest lies in finding whether these networks
are able to perform as well on a different dataset of lower quality archive images. A new
benchmark dataset was created on images from the National Archives of Estonia. Then the
accuracy of determining whether two face images belong to the same person or not was
measured on the new dataset. The network with the strongest reproducible result showed a
strong results on the new benchmark, an accuracy of 91.18%. A suggestion is made by the
author of using the same network for further work on the images from the National Archives
dataset.
recently published. All of those networks had shown good results on a benchmark containing
mostly higher quality images of celebrities. The interest lies in finding whether these networks
are able to perform as well on a different dataset of lower quality archive images. A new
benchmark dataset was created on images from the National Archives of Estonia. Then the
accuracy of determining whether two face images belong to the same person or not was
measured on the new dataset. The network with the strongest reproducible result showed a
strong results on the new benchmark, an accuracy of 91.18%. A suggestion is made by the
author of using the same network for further work on the images from the National Archives
dataset.
Graduation Thesis language
English
Graduation Thesis type
Bachelor - Computer Science
Supervisor(s)
Tambet Matiisen
Defence year
2016