Consistent object representation method for computer vision applications

Kwanghoon Sohn, Jung H. Kim, Winser E. Alexander

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

Abstract

The human visual system uses two-dimensional (2D) boundary information to recognize objects since the shape of the boundary usually contains the pertinent information about an object. Thus, representing a boundary concisely and consistently is necessary for object recognition. In this paper, we propose a consistent object representation method using mean field annealing (MFA) technique for computer vision applications. Since a curvature function computed on a preprocessed smooth boundary, which is obtained by the MFA approach is consistent, we can consistently detect corner points in this curvature function space. Furthermore, the MFA approach preserves the sharpness of corner points very well. Thus, we can detect corner points easier and better with this method than with other existing methods. Ideal corner points rarely exist for a real boundary. They are often rounded due to the smoothing effect of the preprocessing. In addition, a human recognizes both sharp corner points and slightly rounded segments as corner points. Thus, we use `corner sharpness,' which is qualitatively similar to a human's capability of detecting corner points, to increase the robustness of the proposed algorithm.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSociety of Photo-Optical Instrumentation Engineers
Pages163-171
Number of pages9
Volume2353
ISBN (Print)0819416886
Publication statusPublished - 1994 Dec 1
EventIntelligent Robots and Computer Vision XIII: Algorithms and Computer Vision - Boston, MA, USA
Duration: 1994 Oct 311994 Nov 2

Other

OtherIntelligent Robots and Computer Vision XIII: Algorithms and Computer Vision
CityBoston, MA, USA
Period94/10/3194/11/2

Fingerprint

computer vision
Computer vision
Annealing
Object recognition
sharpness
annealing
curvature
function space
preprocessing
smoothing

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Sohn, K., Kim, J. H., & Alexander, W. E. (1994). Consistent object representation method for computer vision applications. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 2353, pp. 163-171). Society of Photo-Optical Instrumentation Engineers.
Sohn, Kwanghoon ; Kim, Jung H. ; Alexander, Winser E. / Consistent object representation method for computer vision applications. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2353 Society of Photo-Optical Instrumentation Engineers, 1994. pp. 163-171
@inproceedings{01879718bf9b4e159edacb4db1b92590,
title = "Consistent object representation method for computer vision applications",
abstract = "The human visual system uses two-dimensional (2D) boundary information to recognize objects since the shape of the boundary usually contains the pertinent information about an object. Thus, representing a boundary concisely and consistently is necessary for object recognition. In this paper, we propose a consistent object representation method using mean field annealing (MFA) technique for computer vision applications. Since a curvature function computed on a preprocessed smooth boundary, which is obtained by the MFA approach is consistent, we can consistently detect corner points in this curvature function space. Furthermore, the MFA approach preserves the sharpness of corner points very well. Thus, we can detect corner points easier and better with this method than with other existing methods. Ideal corner points rarely exist for a real boundary. They are often rounded due to the smoothing effect of the preprocessing. In addition, a human recognizes both sharp corner points and slightly rounded segments as corner points. Thus, we use `corner sharpness,' which is qualitatively similar to a human's capability of detecting corner points, to increase the robustness of the proposed algorithm.",
author = "Kwanghoon Sohn and Kim, {Jung H.} and Alexander, {Winser E.}",
year = "1994",
month = "12",
day = "1",
language = "English",
isbn = "0819416886",
volume = "2353",
pages = "163--171",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Society of Photo-Optical Instrumentation Engineers",

}

Sohn, K, Kim, JH & Alexander, WE 1994, Consistent object representation method for computer vision applications. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 2353, Society of Photo-Optical Instrumentation Engineers, pp. 163-171, Intelligent Robots and Computer Vision XIII: Algorithms and Computer Vision, Boston, MA, USA, 94/10/31.

Consistent object representation method for computer vision applications. / Sohn, Kwanghoon; Kim, Jung H.; Alexander, Winser E.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2353 Society of Photo-Optical Instrumentation Engineers, 1994. p. 163-171.

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

TY - GEN

T1 - Consistent object representation method for computer vision applications

AU - Sohn, Kwanghoon

AU - Kim, Jung H.

AU - Alexander, Winser E.

PY - 1994/12/1

Y1 - 1994/12/1

N2 - The human visual system uses two-dimensional (2D) boundary information to recognize objects since the shape of the boundary usually contains the pertinent information about an object. Thus, representing a boundary concisely and consistently is necessary for object recognition. In this paper, we propose a consistent object representation method using mean field annealing (MFA) technique for computer vision applications. Since a curvature function computed on a preprocessed smooth boundary, which is obtained by the MFA approach is consistent, we can consistently detect corner points in this curvature function space. Furthermore, the MFA approach preserves the sharpness of corner points very well. Thus, we can detect corner points easier and better with this method than with other existing methods. Ideal corner points rarely exist for a real boundary. They are often rounded due to the smoothing effect of the preprocessing. In addition, a human recognizes both sharp corner points and slightly rounded segments as corner points. Thus, we use `corner sharpness,' which is qualitatively similar to a human's capability of detecting corner points, to increase the robustness of the proposed algorithm.

AB - The human visual system uses two-dimensional (2D) boundary information to recognize objects since the shape of the boundary usually contains the pertinent information about an object. Thus, representing a boundary concisely and consistently is necessary for object recognition. In this paper, we propose a consistent object representation method using mean field annealing (MFA) technique for computer vision applications. Since a curvature function computed on a preprocessed smooth boundary, which is obtained by the MFA approach is consistent, we can consistently detect corner points in this curvature function space. Furthermore, the MFA approach preserves the sharpness of corner points very well. Thus, we can detect corner points easier and better with this method than with other existing methods. Ideal corner points rarely exist for a real boundary. They are often rounded due to the smoothing effect of the preprocessing. In addition, a human recognizes both sharp corner points and slightly rounded segments as corner points. Thus, we use `corner sharpness,' which is qualitatively similar to a human's capability of detecting corner points, to increase the robustness of the proposed algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0028748651&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028748651&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0819416886

VL - 2353

SP - 163

EP - 171

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

PB - Society of Photo-Optical Instrumentation Engineers

ER -

Sohn K, Kim JH, Alexander WE. Consistent object representation method for computer vision applications. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2353. Society of Photo-Optical Instrumentation Engineers. 1994. p. 163-171