English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Pixel-based versus correspondence-based representations of human faces: Implications for sex discrimination

Troje, N., & Vetter, T. (1996). Pixel-based versus correspondence-based representations of human faces: Implications for sex discrimination. Perception, 25(ECVP Abstract Supplement), 52.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-EB3E-5 Version Permalink: http://hdl.handle.net/21.11116/0000-0005-F1EE-F
Genre: Meeting Abstract

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Troje, NF1, 2, Author              
Vetter, T1, 2, Author              
Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: In human perception, as well as in machine vision, a crucial step in solving any object recognition task is an appropriate description of the object class under consideration. We emphasise this issue when considering the object class `human faces'. We discuss different representations that can be characterised by the degree of alignment between the images they provide for. The representations used span the whole range between a purely pixel-based image representation and a sophisticated model-based representation derived from the pixel-to-pixel correspondence between the faces [Vetter and Troje, 1995, in Mustererkennung Eds G Sagerer, S Posch, F Kummert (Berlin: Springer)]. The usefulness of these representations for sex classification was compared. This was done by first applying a Karhunen -- Loewe transformation on the representation to orthogonalise the data. A linear classifier was trained by means of a gradient-descent procedure. The classification error in a completely cross-validated simulation ranged from 15 in the simplest version of the pixel-based representation to 2.5 for the correspondence-based representation. However, even with intermediate representations very good performance was achieved.

Details

show
hide
Language(s):
 Dates: 1996-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: 1893
DOI: 10.1068/v96l1112
 Degree: -

Event

show
hide
Title: 19th European Conference on Visual Perception (ECVP 1996)
Place of Event: Strasbourg, France
Start-/End Date: 1996-09-09 - 1996-09-13

Legal Case

show

Project information

show

Source 1

show
hide
Title: Perception
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: London : Pion Ltd.
Pages: - Volume / Issue: 25 (ECVP Abstract Supplement) Sequence Number: - Start / End Page: 52 Identifier: ISSN: 0301-0066
CoNE: https://pure.mpg.de/cone/journals/resource/954925509369