Learning and Extracting Priori-driven Representations of Face Images to Understand the Human Visual Recognition System

Carlos E. Thomaz, Gilson A. Giraldi, Duncan F. Gillies, Daniel Rueckert

2017

Abstract

Faces are familiar objects that can be easily perceived and recognized by humans. However, the computational modeling of such apparently natural and heritable human ability remains challenging. This chapter shows theoretical and empirical results about the processes underlying face perception using frontal and well-framed images as stimuli. Exploring eye movements of a number of participants on distinct classification tasks, we have implemented a multivariate statistical method that combines variance information with focused human visual attention. Our experimental results carried out on publicly available face databases have indicated that we might emulate the face perception processing as a pattern-based coding scheme rather than a feature-based one to properly explain the proficiency of the human visual system in recognizing face information.

Paper Citation

in Harvard Style

Thomaz C., Giraldi G., Gillies D. and Rueckert D. (2017). Learning and Extracting Priori-driven Representations of Face Images to Understand the Human Visual Recognition System.In OPPORTUNITIES AND CHALLENGES for European Projects - Volume 1: EPS Portugal 2017/2018, ISBN 978-989-758-361-2, pages 42-55. DOI: 10.5220/0008861900420055

in Bibtex Style

@conference{eps portugal 2017/201817,
author={Carlos E. Thomaz and Gilson A. Giraldi and Duncan F. Gillies and Daniel Rueckert},
title={Learning and Extracting Priori-driven Representations of Face Images to Understand the Human Visual Recognition System},
booktitle={OPPORTUNITIES AND CHALLENGES for European Projects - Volume 1: EPS Portugal 2017/2018,},
year={2017},
pages={42-55},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008861900420055},
isbn={978-989-758-361-2},
}

in EndNote Style

TY - CONF

JO - OPPORTUNITIES AND CHALLENGES for European Projects - Volume 1: EPS Portugal 2017/2018,
TI - Learning and Extracting Priori-driven Representations of Face Images to Understand the Human Visual Recognition System
SN - 978-989-758-361-2
AU - Thomaz C.
AU - Giraldi G.
AU - Gillies D.
AU - Rueckert D.
PY - 2017
SP - 42
EP - 55
DO - 10.5220/0008861900420055