Does automatic human face categorization depend on head orientation?

Cortex ◽  
2021 ◽  
Author(s):  
Charles C.-F. Or ◽  
Talia L. Retter ◽  
Bruno Rossion
Keyword(s):  
Head Orientation ◽  
Human Face ◽  
Face Categorization

CATEGORIZATION AND IDENTIFICATION OF HUMAN FACE IMAGES BY NEURAL NETWORKS: A REVIEW OF THE LINEAR AUTOASSOCIATIVE AND PRINCIPAL COMPONENT APPROACHES

1994 ◽  
Vol 02 (03) ◽  
pp. 413-429 ◽  
Author(s):  
D. VALENTIN ◽  
H. ABDI ◽  
A.J. O’TOOLE
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Face Processing ◽  
Linear Models ◽  
Network Models ◽  
Principal Component ◽  
Human Face ◽  
Neural Network Models ◽  
Face Images ◽  
Face Categorization

Recent statistical/neural network models of face processing suggest that faces can be efficiently represented in terms of the eigendecomposition of a matrix storing pixel-based descriptions of a set of face images. The studies presented here support the idea that the information useful for solving seemingly complex tasks such as face categorization or identification can be described using simple linear models (linear autoassociator or principal component analysis) in conjunction with a pixel-based coding of the faces.

scholarly journals Granule-Based-Classifier (GbC): A Lattice Computing Scheme Applied on Tree Data Structures

Mathematics ◽  
2021 ◽  
Vol 9 (22) ◽  
pp. 2889
Author(s):  
Vassilis G. Kaburlasos ◽  
Chris Lytridis ◽  
Eleni Vrochidou ◽  
Christos Bazinas ◽  
George A. Papakostas ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Data Structures ◽  
Real World ◽  
Head Orientation ◽  
Human Face ◽  
Human Face Recognition ◽  
Face Representation ◽  
Tree Data ◽  
Tree Data Structure ◽  
Logic Reasoning

Social robots keep proliferating. A critical challenge remains their sensible interaction with humans, especially in real world applications. Hence, computing with real world semantics is instrumental. Recently, the Lattice Computing (LC) paradigm has been proposed with a capacity to compute with semantics represented by partial order in a mathematical lattice data domain. In the aforementioned context, this work proposes a parametric LC classifier, namely a Granule-based-Classifier (GbC), applicable in a mathematical lattice (T,⊑) of tree data structures, each of which represents a human face. A tree data structure here emerges from 68 facial landmarks (points) computed in a data preprocessing step by the OpenFace software. The proposed (tree) representation retains human anonymity during data processing. Extensive computational experiments regarding three different pattern recognition problems, namely (1) head orientation, (2) facial expressions, and (3) human face recognition, demonstrate GbC capacities, including good classification results, and a common human face representation in different pattern recognition problems, as well as data induced granular rules in (T,⊑) that allow for (a) explainable decision-making, (b) tunable generalization enabled also by formal logic/reasoning techniques, and (c) an inherent capacity for modular data fusion extensions. The potential of the proposed techniques is discussed.

scholarly journals The effects of gaze and head orientation on the speed of face categorization during RSVP

2021 ◽  
Vol 21 (9) ◽  
pp. 1942
Author(s):  
Charles C.-F. Or ◽  
Benjamin K. Goh ◽  
Alan L.F. Lee
Keyword(s):  
Head Orientation ◽  
Face Categorization

scholarly journals The speed of human face categorization

2018 ◽  
Vol 18 (10) ◽  
pp. 356
Author(s):  
Talia Retter ◽  
Fang Jiang ◽  
Bruno Rossion
Keyword(s):  
Human Face ◽  
Face Categorization

Newborn's Preference for Faces

1996 ◽  
Vol 1 (3) ◽  
pp. 200-205 ◽  
Author(s):  
Carlo Umiltà ◽  
Francesca Simion ◽  
Eloisa Valenza
Keyword(s):  
Visual System ◽  
Structural Properties ◽  
Sensory Properties ◽  
Human Face ◽  
System Experiment ◽  
Face Experiment

Four experiments were aimed at elucidating some aspects of the preference for facelike patterns in newborns. Experiment 1 showed a preference for a stimulus whose components were located in the correct arrangement for a human face. Experiment 2 showed a preference for stimuli that had optimal sensory properties for the newborn visual system. Experiment 3 showed that babies directed their attention to a facelike pattern even when it was presented simultaneously with a non-facelike stimulus with optimal sensory properties. Experiment 4 showed the preference for facelike patterns in the temporal hemifield but not in the nasal hemifield. It was concluded that newborns' preference for facelike patterns reflects the activity of a subcortical system which is sensitive to the structural properties of the stimulus.

Discriminability and the Preferred Level of Face Categorization

2007 ◽  
Author(s):  
Christopher J. D'lauro ◽  
James W. Tanaka ◽  
Tim Curran
Keyword(s):  
Face Categorization
Sign in / Sign up

Export Citation Format

Share Document