Advanced biologically plausible algorithms for low-level image processing

Valentina I. Gusakova, Lubov N. Podladchikova, Dmitry G. Shaposhnikov, Sergey N. Markin, Alexander V. Golovan, Seong Whan Lee

Research output: Contribution to journalArticle

Abstract

At present, in computer vision, the approach based on modeling the biological vision mechanisms is extensively developed. However, up to now, real world image processing has no effective solution in frameworks of both biologically inspired and conventional approaches. Evidently, new algorithms and system architectures based on advanced biological motivation should be developed for solution of computational problems related to this visual task. Basic problems that should be solved for creation of effective artificial visual system to process real world images are a search for new algorithms of low-level image processing that, in a great extent, determine system performance. In the present paper, the results of psychophysical experiments and several advanced biologically motivated algorithms for low-level processing are presented. These algorithms are based on local space-variant filter, context encoding visual information presented in the center of input window, and automatic detection of perceptually important image fragments. The core of latter algorithm (the cascade method) are using local feature conjunctions such as noncolinear oriented segment and composite feature map formation. Developed algorithms were integrated into foveal active vision model, the MARR. It is supposed that proposed algorithms may significantly improve model performance while real world image processing during memorizing, search, and recognition.

Original languageEnglish
Pages (from-to)377-385
Number of pages9
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume3837
Publication statusPublished - 1999
Externally publishedYes

Fingerprint

image processing
Image Processing
Image processing
visual tasks
Active Vision
conjunction
Visual System
Local Features
computer vision
Performance Model
System Architecture
Computer Vision
Computer vision
Cascade
System Performance
cascades
Fragment
coding
Encoding
Composite

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Gusakova, V. I., Podladchikova, L. N., Shaposhnikov, D. G., Markin, S. N., Golovan, A. V., & Lee, S. W. (1999). Advanced biologically plausible algorithms for low-level image processing. Proceedings of SPIE - The International Society for Optical Engineering, 3837, 377-385.

Advanced biologically plausible algorithms for low-level image processing. / Gusakova, Valentina I.; Podladchikova, Lubov N.; Shaposhnikov, Dmitry G.; Markin, Sergey N.; Golovan, Alexander V.; Lee, Seong Whan.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 3837, 1999, p. 377-385.

Research output: Contribution to journalArticle

Gusakova, VI, Podladchikova, LN, Shaposhnikov, DG, Markin, SN, Golovan, AV & Lee, SW 1999, 'Advanced biologically plausible algorithms for low-level image processing', Proceedings of SPIE - The International Society for Optical Engineering, vol. 3837, pp. 377-385.
Gusakova, Valentina I. ; Podladchikova, Lubov N. ; Shaposhnikov, Dmitry G. ; Markin, Sergey N. ; Golovan, Alexander V. ; Lee, Seong Whan. / Advanced biologically plausible algorithms for low-level image processing. In: Proceedings of SPIE - The International Society for Optical Engineering. 1999 ; Vol. 3837. pp. 377-385.
@article{3f76570a5b154c869fb3a62ecd0d8fa1,
title = "Advanced biologically plausible algorithms for low-level image processing",
abstract = "At present, in computer vision, the approach based on modeling the biological vision mechanisms is extensively developed. However, up to now, real world image processing has no effective solution in frameworks of both biologically inspired and conventional approaches. Evidently, new algorithms and system architectures based on advanced biological motivation should be developed for solution of computational problems related to this visual task. Basic problems that should be solved for creation of effective artificial visual system to process real world images are a search for new algorithms of low-level image processing that, in a great extent, determine system performance. In the present paper, the results of psychophysical experiments and several advanced biologically motivated algorithms for low-level processing are presented. These algorithms are based on local space-variant filter, context encoding visual information presented in the center of input window, and automatic detection of perceptually important image fragments. The core of latter algorithm (the cascade method) are using local feature conjunctions such as noncolinear oriented segment and composite feature map formation. Developed algorithms were integrated into foveal active vision model, the MARR. It is supposed that proposed algorithms may significantly improve model performance while real world image processing during memorizing, search, and recognition.",
author = "Gusakova, {Valentina I.} and Podladchikova, {Lubov N.} and Shaposhnikov, {Dmitry G.} and Markin, {Sergey N.} and Golovan, {Alexander V.} and Lee, {Seong Whan}",
year = "1999",
language = "English",
volume = "3837",
pages = "377--385",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

TY - JOUR

T1 - Advanced biologically plausible algorithms for low-level image processing

AU - Gusakova, Valentina I.

AU - Podladchikova, Lubov N.

AU - Shaposhnikov, Dmitry G.

AU - Markin, Sergey N.

AU - Golovan, Alexander V.

AU - Lee, Seong Whan

PY - 1999

Y1 - 1999

N2 - At present, in computer vision, the approach based on modeling the biological vision mechanisms is extensively developed. However, up to now, real world image processing has no effective solution in frameworks of both biologically inspired and conventional approaches. Evidently, new algorithms and system architectures based on advanced biological motivation should be developed for solution of computational problems related to this visual task. Basic problems that should be solved for creation of effective artificial visual system to process real world images are a search for new algorithms of low-level image processing that, in a great extent, determine system performance. In the present paper, the results of psychophysical experiments and several advanced biologically motivated algorithms for low-level processing are presented. These algorithms are based on local space-variant filter, context encoding visual information presented in the center of input window, and automatic detection of perceptually important image fragments. The core of latter algorithm (the cascade method) are using local feature conjunctions such as noncolinear oriented segment and composite feature map formation. Developed algorithms were integrated into foveal active vision model, the MARR. It is supposed that proposed algorithms may significantly improve model performance while real world image processing during memorizing, search, and recognition.

AB - At present, in computer vision, the approach based on modeling the biological vision mechanisms is extensively developed. However, up to now, real world image processing has no effective solution in frameworks of both biologically inspired and conventional approaches. Evidently, new algorithms and system architectures based on advanced biological motivation should be developed for solution of computational problems related to this visual task. Basic problems that should be solved for creation of effective artificial visual system to process real world images are a search for new algorithms of low-level image processing that, in a great extent, determine system performance. In the present paper, the results of psychophysical experiments and several advanced biologically motivated algorithms for low-level processing are presented. These algorithms are based on local space-variant filter, context encoding visual information presented in the center of input window, and automatic detection of perceptually important image fragments. The core of latter algorithm (the cascade method) are using local feature conjunctions such as noncolinear oriented segment and composite feature map formation. Developed algorithms were integrated into foveal active vision model, the MARR. It is supposed that proposed algorithms may significantly improve model performance while real world image processing during memorizing, search, and recognition.

UR - http://www.scopus.com/inward/record.url?scp=0033312361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033312361&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0033312361

VL - 3837

SP - 377

EP - 385

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -