This paper describes an original methodology for the improvement of the reliability of results in classification systems based on 3D images. More in detail, it is based on the knowledge of the uncertainty of the features constituting the 3D image and on a suitable statistical approach providing a confidence level to the classification result. These pieces of information are then managed in order to improve the classification performance. The first experiments show that, compared with a traditional approach (which generally does not take into account the uncertainty on 3D features), the proposed methodology allows to significantly improve the classification performance even in a scenario characterized by a high uncertainty.

Managing the uncertainty for face classification with 3D features

GASPARETTO, MICHELE;ZAPPA, EMANUELE;
2014-01-01

Abstract

This paper describes an original methodology for the improvement of the reliability of results in classification systems based on 3D images. More in detail, it is based on the knowledge of the uncertainty of the features constituting the 3D image and on a suitable statistical approach providing a confidence level to the classification result. These pieces of information are then managed in order to improve the classification performance. The first experiments show that, compared with a traditional approach (which generally does not take into account the uncertainty on 3D features), the proposed methodology allows to significantly improve the classification performance even in a scenario characterized by a high uncertainty.
2014
Conference Record - IEEE Instrumentation and Measurement Technology Conference
9781467363853
9781467363853
3D features; decision support systems; face recognition; image classification; measurement uncertainty; Electrical and Electronic Engineering
File in questo prodotto:
File Dimensione Formato  
I2MTC2014_Proceedings_biometria.pdf

Accesso riservato

Descrizione: Paper
: Publisher’s version
Dimensione 316.97 kB
Formato Adobe PDF
316.97 kB Adobe PDF   Visualizza/Apri

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/11311/970540
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 2
social impact