Help Privacy Policy Disclaimer
  Advanced SearchBrowse


  Study of Human Classification using Psychophysics and Machine Learning

Graf, A., Wichmann, F., Bülthoff, H., & Schölkopf, B. (2003). Study of Human Classification using Psychophysics and Machine Learning. Poster presented at 6. Tübinger Wahrnehmungskonferenz (TWK 2003), Tübingen, Germany.

Item is


show Files




Graf, ABA1, 2, 3, Author              
Wichmann, FA1, 3, Author              
Bülthoff, HH2, 3, Author              
Schölkopf, B1, 3, Author              
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              
3Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              


Free keywords: -
 Abstract: We attempt to reach a better understanding of classication in humans using both psychophysical and machine learning techniques. In our psychophysical paradigm the stimuli presented to the human subjects are modied using machine learning algorithms according to their responses. Frontal views of human faces taken from a processed version of the MPI face database are employed for a gender classication task. The processing assures that all heads have same mean intensity, same pixel-surface area and are centered. This processing stage is followed by a smoothing of the database in order to eliminate, as much as possible, scanning artifacts. Principal Component Analysis is used to obtain a low-dimensional representation of the faces in the database. A subject is asked to classify the faces and experimental parameters such as class (i.e. female/male), condence ratings and reaction times are recorded. A mean classication error of 14.5 is measured and, on average, 0.5 males are classied as females and 21.3females as males. The mean reaction time for the correctly classied faces is 1229 +- 252 [ms] whereas the incorrectly classied faces have a mean reaction time of 1769 +- 304 [ms] showing that the reaction times increase with the subject's classi- cation error. Reaction times are also shown to decrease with increasing condence, both for the correct and incorrect classications. Classication errors, reaction times and condence ratings are then correlated to concepts of machine learning such as separating hyperplane obtained when considering Support Vector Machines, Relevance Vector Machines, boosted Prototype and K-means Learners. Elements near the separating hyperplane are found to be classied with more errors than those away from it. In addition, the subject's condence increases when moving away from the hyperplane. A preliminary analysis on the available small number of subjects indicates that K-means classication seems to re ect the subject's classication behavior best. The above learnersare then used to generate \special" elements, or representations, of the low-dimensional database according to the labels given by the subject. A memory experiment follows where the representations are shown together with faces seen or unseen during the classication experiment. This experiment aims to assess the representations by investigating whether some representations, or special elements, are classied as \seen before" despite that they never appeared in the classication experiment, possibly hinting at their use during human classication.


 Dates: 2003-02
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 2090
 Degree: -


Title: 6. Tübinger Wahrnehmungskonferenz (TWK 2003)
Place of Event: Tübingen, Germany
Start-/End Date: 2003-02-21 - 2003-02-23

Legal Case


Project information


Source 1

Title: 6. Tübinger Wahrnehmungskonferenz: Sixth Perception Conference at Tübingen, TWK 2003
Source Genre: Proceedings
Bülthoff, HH1, Editor            
Gegenfurtner, KR, Editor            
Mallot, HA, Editor            
Ulrich, R, Editor
Wichmann, FA1, Editor            
1 Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794            
Publ. Info: Kirchentellinsfurt, Germany : Knirsch
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 149 Identifier: ISBN: 3-927091-62-6