Object categorization using biologically inspired nodemaps and the HITEC categorization system

Adam Csapo, Barna Resko, D. Tikk, P. Baranyi

Research output: Contribution to journalArticle

Abstract

The computerized modeling of cognitive visual information has been a research field of great interest in the past several decades. The research field is interesting not only from a biological perspective, but also from an engineering point of view when systems are developed that aim to achieve similar goals as biological cognitive systems. This paper briefly describes a general framework for the extraction and systematic storage of low-level visual features, and demonstrates its applicability in image categorization using a linear categorization algorithm originally developed for the characterization of text documents. The performance of the algorithm together with the newly developed feature array was evaluated using the Caltech 101 database. Extremely high (95% and higher) success rates were achieved when distinguishing between pairs of categories using independent test images. Efforts were made to scale up the number of categories using a hierarchical, branch-and-bound decision tree, with limited success.

Original languageEnglish
Pages (from-to)573-580
Number of pages8
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume13
Issue number5
Publication statusPublished - 2009

Fingerprint

Cognitive systems
Decision trees

Keywords

  • Cognitive informatics
  • HITEC
  • Image categorization
  • Visual feature array

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

@article{060e8856e46c4d63a4381ec9d5feea5d,
title = "Object categorization using biologically inspired nodemaps and the HITEC categorization system",
abstract = "The computerized modeling of cognitive visual information has been a research field of great interest in the past several decades. The research field is interesting not only from a biological perspective, but also from an engineering point of view when systems are developed that aim to achieve similar goals as biological cognitive systems. This paper briefly describes a general framework for the extraction and systematic storage of low-level visual features, and demonstrates its applicability in image categorization using a linear categorization algorithm originally developed for the characterization of text documents. The performance of the algorithm together with the newly developed feature array was evaluated using the Caltech 101 database. Extremely high (95{\%} and higher) success rates were achieved when distinguishing between pairs of categories using independent test images. Efforts were made to scale up the number of categories using a hierarchical, branch-and-bound decision tree, with limited success.",
keywords = "Cognitive informatics, HITEC, Image categorization, Visual feature array",
author = "Adam Csapo and Barna Resko and D. Tikk and P. Baranyi",
year = "2009",
language = "English",
volume = "13",
pages = "573--580",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "5",

}

TY - JOUR

T1 - Object categorization using biologically inspired nodemaps and the HITEC categorization system

AU - Csapo, Adam

AU - Resko, Barna

AU - Tikk, D.

AU - Baranyi, P.

PY - 2009

Y1 - 2009

N2 - The computerized modeling of cognitive visual information has been a research field of great interest in the past several decades. The research field is interesting not only from a biological perspective, but also from an engineering point of view when systems are developed that aim to achieve similar goals as biological cognitive systems. This paper briefly describes a general framework for the extraction and systematic storage of low-level visual features, and demonstrates its applicability in image categorization using a linear categorization algorithm originally developed for the characterization of text documents. The performance of the algorithm together with the newly developed feature array was evaluated using the Caltech 101 database. Extremely high (95% and higher) success rates were achieved when distinguishing between pairs of categories using independent test images. Efforts were made to scale up the number of categories using a hierarchical, branch-and-bound decision tree, with limited success.

AB - The computerized modeling of cognitive visual information has been a research field of great interest in the past several decades. The research field is interesting not only from a biological perspective, but also from an engineering point of view when systems are developed that aim to achieve similar goals as biological cognitive systems. This paper briefly describes a general framework for the extraction and systematic storage of low-level visual features, and demonstrates its applicability in image categorization using a linear categorization algorithm originally developed for the characterization of text documents. The performance of the algorithm together with the newly developed feature array was evaluated using the Caltech 101 database. Extremely high (95% and higher) success rates were achieved when distinguishing between pairs of categories using independent test images. Efforts were made to scale up the number of categories using a hierarchical, branch-and-bound decision tree, with limited success.

KW - Cognitive informatics

KW - HITEC

KW - Image categorization

KW - Visual feature array

UR - http://www.scopus.com/inward/record.url?scp=77749314689&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77749314689&partnerID=8YFLogxK

M3 - Article

VL - 13

SP - 573

EP - 580

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 5

ER -