English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Poster

Study of Human Classification using Psychophysics and Machine Learning

MPS-Authors
/persons/resource/persons83943

Graf,  ABA
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84314

Wichmann,  FA
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83839

Bülthoff,  HH
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84193

Schölkopf,  B
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

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.


Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-DD22-1
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.