Visual cortex inspired vertex and corner detection

Ádám B. Csapó, András Róka, P. Baranyi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Sets of corners and crossings in images characterize the shape and position of visual objects. The detection of these features not only supports, but is also a necessary condition to successful object recognition in human visual perception. Recent results in cognitive research have shown that the visual cortex has a mechanism for the detection of corners and crosses, and makes use of this in higher-level visual processing. In this paper, we propose an artificial neural architecture as a possible model for corner- and cross-sensitive cells - as an extension to the VFA (Visual Feature Array) module. The model assumes a hierarchical structure of node-, endpoint-, cross- and corner-sensitive cells. Through test results, the benefits of such a hierarchical structure will be shown in terms of higher-level object recognition.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Mechatronics, ICM
Pages551-556
Number of pages6
DOIs
Publication statusPublished - 2006
Event2006 IEEE International Conference on Mechatronics, ICM - Budapest, Hungary
Duration: Jul 3 2006Jul 5 2006

Other

Other2006 IEEE International Conference on Mechatronics, ICM
CountryHungary
CityBudapest
Period7/3/067/5/06

Fingerprint

Object recognition
Processing

Keywords

  • Complex cell
  • Corner
  • Crossing
  • Simple cell
  • VFA
  • Visual cortex

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Csapó, Á. B., Róka, A., & Baranyi, P. (2006). Visual cortex inspired vertex and corner detection. In 2006 IEEE International Conference on Mechatronics, ICM (pp. 551-556). [4018421] https://doi.org/10.1109/ICMECH.2006.252586

Visual cortex inspired vertex and corner detection. / Csapó, Ádám B.; Róka, András; Baranyi, P.

2006 IEEE International Conference on Mechatronics, ICM. 2006. p. 551-556 4018421.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Csapó, ÁB, Róka, A & Baranyi, P 2006, Visual cortex inspired vertex and corner detection. in 2006 IEEE International Conference on Mechatronics, ICM., 4018421, pp. 551-556, 2006 IEEE International Conference on Mechatronics, ICM, Budapest, Hungary, 7/3/06. https://doi.org/10.1109/ICMECH.2006.252586
Csapó ÁB, Róka A, Baranyi P. Visual cortex inspired vertex and corner detection. In 2006 IEEE International Conference on Mechatronics, ICM. 2006. p. 551-556. 4018421 https://doi.org/10.1109/ICMECH.2006.252586
Csapó, Ádám B. ; Róka, András ; Baranyi, P. / Visual cortex inspired vertex and corner detection. 2006 IEEE International Conference on Mechatronics, ICM. 2006. pp. 551-556
@inproceedings{66e3e7ac5d1c4281b90385fdad1fa0da,
title = "Visual cortex inspired vertex and corner detection",
abstract = "Sets of corners and crossings in images characterize the shape and position of visual objects. The detection of these features not only supports, but is also a necessary condition to successful object recognition in human visual perception. Recent results in cognitive research have shown that the visual cortex has a mechanism for the detection of corners and crosses, and makes use of this in higher-level visual processing. In this paper, we propose an artificial neural architecture as a possible model for corner- and cross-sensitive cells - as an extension to the VFA (Visual Feature Array) module. The model assumes a hierarchical structure of node-, endpoint-, cross- and corner-sensitive cells. Through test results, the benefits of such a hierarchical structure will be shown in terms of higher-level object recognition.",
keywords = "Complex cell, Corner, Crossing, Simple cell, VFA, Visual cortex",
author = "Csap{\'o}, {{\'A}d{\'a}m B.} and Andr{\'a}s R{\'o}ka and P. Baranyi",
year = "2006",
doi = "10.1109/ICMECH.2006.252586",
language = "English",
isbn = "0780397134",
pages = "551--556",
booktitle = "2006 IEEE International Conference on Mechatronics, ICM",

}

TY - GEN

T1 - Visual cortex inspired vertex and corner detection

AU - Csapó, Ádám B.

AU - Róka, András

AU - Baranyi, P.

PY - 2006

Y1 - 2006

N2 - Sets of corners and crossings in images characterize the shape and position of visual objects. The detection of these features not only supports, but is also a necessary condition to successful object recognition in human visual perception. Recent results in cognitive research have shown that the visual cortex has a mechanism for the detection of corners and crosses, and makes use of this in higher-level visual processing. In this paper, we propose an artificial neural architecture as a possible model for corner- and cross-sensitive cells - as an extension to the VFA (Visual Feature Array) module. The model assumes a hierarchical structure of node-, endpoint-, cross- and corner-sensitive cells. Through test results, the benefits of such a hierarchical structure will be shown in terms of higher-level object recognition.

AB - Sets of corners and crossings in images characterize the shape and position of visual objects. The detection of these features not only supports, but is also a necessary condition to successful object recognition in human visual perception. Recent results in cognitive research have shown that the visual cortex has a mechanism for the detection of corners and crosses, and makes use of this in higher-level visual processing. In this paper, we propose an artificial neural architecture as a possible model for corner- and cross-sensitive cells - as an extension to the VFA (Visual Feature Array) module. The model assumes a hierarchical structure of node-, endpoint-, cross- and corner-sensitive cells. Through test results, the benefits of such a hierarchical structure will be shown in terms of higher-level object recognition.

KW - Complex cell

KW - Corner

KW - Crossing

KW - Simple cell

KW - VFA

KW - Visual cortex

UR - http://www.scopus.com/inward/record.url?scp=34250822401&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250822401&partnerID=8YFLogxK

U2 - 10.1109/ICMECH.2006.252586

DO - 10.1109/ICMECH.2006.252586

M3 - Conference contribution

AN - SCOPUS:34250822401

SN - 0780397134

SN - 9780780397132

SP - 551

EP - 556

BT - 2006 IEEE International Conference on Mechatronics, ICM

ER -