Face recognition has a wide practical applicability in various contexts, for example, detecting students attending a lecture at university, identifying members in a gym or monitoring people in an airport. Recent methods based on Convolutional Neural Network (CNN), such as FaceNet, achieved state-of-the-art performance in face recognition. Inspired from this work, we propose a pipeline to improve face recognition systems based on Center loss. The main advantage is that our approach does not suffer from data expansion as in Triplet loss. Our pipeline is capable of cleaning an existing face dataset to improve the recognition performance or creating one from scratch. We present detailed experiments to show characteristics and performance of the pipeline. In addition, a small-scale application for face recognition that makes use of the proposed cleaning process is presented.

A Pipeline to Improve Face Recognition Datasets and Applications

I. Gallo
;
S. Nawaz;A. Calefati;
2018-01-01

Abstract

Face recognition has a wide practical applicability in various contexts, for example, detecting students attending a lecture at university, identifying members in a gym or monitoring people in an airport. Recent methods based on Convolutional Neural Network (CNN), such as FaceNet, achieved state-of-the-art performance in face recognition. Inspired from this work, we propose a pipeline to improve face recognition systems based on Center loss. The main advantage is that our approach does not suffer from data expansion as in Triplet loss. Our pipeline is capable of cleaning an existing face dataset to improve the recognition performance or creating one from scratch. We present detailed experiments to show characteristics and performance of the pipeline. In addition, a small-scale application for face recognition that makes use of the proposed cleaning process is presented.
2018
2018 International Conference on Image and Vision Computing New Zealand (IVCNZ)
9781728101255
International Conference on Image and Vision Computing New Zealand
Auckland, New Zealand
19-21 November 2018
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11383/2083803
 Attenzione

L'Ateneo sottopone a validazione solo i file PDF allegati

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 0
social impact