License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/DagSemProc.06031.5
URN: urn:nbn:de:0030-drops-5756
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2006/575/
Go to the corresponding Portal

Westphal, Günter ; von der Malsburg, Christoph ; Würtz, Rolf P.

Feature-driven Emergence of Model Graphs for Object Recognition and Categorization

pdf-format:
06031.WuertzRolf.Paper.575.pdf (2 MB)

Abstract

An important requirement for the expression of cognitive structures
is the ability to form mental objects by rapidly binding together
constituent parts. In this sense, one may conceive the brain's data
structure to have the form of graphs whose nodes are labeled with
elementary features. These provide a versatile data format with the
additional ability to render the structure of any mental object.
Because of the multitude of possible object variations the graphs
are required to be dynamic. Upon presentation of an image a
so-called model graph should rapidly emerge by binding together
memorized subgraphs derived from earlier learning examples driven by the
image features. In this model, the richness and flexibility of the
mind is made possible by a combinatorical game of immense
complexity. Consequently, the emergence of model graphs is a
laborious task which, in computer vision, has most often been
disregarded in favor of employing model graphs tailored to specific
object categories like, for instance, faces in frontal pose.
Recognition or categorization of arbitrary objects, however, demands
dynamic graphs.

In this work we propose a form of graph dynamics, which proceeds in
two steps. In the first step component classifiers, which decide
whether a feature is present in an image, are learned from training
images. For processing arbitrary objects, features are small
localized grid graphs, so-called parquet graphs, whose nodes are
attributed with Gabor amplitudes. Through combination of these
classifiers into a linear discriminant that conforms to Linsker's
infomax principle a weighted majority voting scheme is implemented.
It allows for preselection of salient learning examples, so-called
model candidates, and likewise for preselection of categories the
object in the presented image supposably belongs to. Each model
candidate is verified in a second step using a variant of elastic
graph matching, a standard correspondence-based technique for face
and object recognition. To further differentiate between model
candidates with similar features it is asserted that the features be
in similar spatial arrangement for the model to be selected. Model
graphs are constructed dynamically by assembling model features into
larger graphs according to their spatial arrangement. From the
viewpoint of pattern recognition, the presented technique is a
combination of a discriminative (feature-based) and a generative
(correspondence-based) classifier while the majority voting scheme
implemented in the feature-based part is an extension of existing
multiple feature subset methods.

We report the results of experiments on standard databases for
object recognition and categorization. The method achieved high
recognition rates on identity, object category, pose, and
illumination type. Unlike many other models the presented
technique can also cope with varying background, multiple objects,
and partial occlusion.

BibTeX - Entry

@InProceedings{westphal_et_al:DagSemProc.06031.5,
  author =	{Westphal, G\"{u}nter and von der Malsburg, Christoph and W\"{u}rtz, Rolf P.},
  title =	{{Feature-driven Emergence of Model Graphs for Object Recognition and Categorization}},
  booktitle =	{Organic Computing - Controlled Emergence},
  pages =	{1--46},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2006},
  volume =	{6031},
  editor =	{Kirstie Bellman and Peter Hofmann and Christian M\"{u}ller-Schloer and Hartmut Schmeck and Rolf W\"{u}rtz},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2006/575},
  URN =		{urn:nbn:de:0030-drops-5756},
  doi =		{10.4230/DagSemProc.06031.5},
  annote =	{Keywords: Graph matching, recognition, categorization, computer vision, self-organization, emergence}
}

Keywords: Graph matching, recognition, categorization, computer vision, self-organization, emergence
Collection: 06031 - Organic Computing - Controlled Emergence
Issue Date: 2006
Date of publication: 16.05.2006

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI