Matching and retrieval based on the vocabulary and grammar of color patterns

A. Mojsilovic, Jelena Kovacevic, J. Hu, R. J. Safranek, S. K. Ganapathy

Research output: Contribution to conferencePaper

Abstract

While it is recognized that images are described through color, texture and shapes of objects in the scene, the general image understanding is still difficult. Thus, to perform image retrieval in a human-like manner one has to chose a specific domain, understand how users achieve similarity within that domain and then build a system that duplicates human performance. Since color and texture are fundamental aspects of human perception we propose a set of techniques for retrieval of color patterns. To determine how humans judge similarity of color patterns we performed a subjective study. Based on the results of the study five most relevant visual categories for the perception of pattern similarity were identified. We also determined the hierarchy of rules governing the use of these categories. Based on these results we designed a system which accepts one or more texture images as input, and depending on the query, produces a set of choices that follow human behavior in pattern matching. Processing steps in our model follow those of the human visual system, resulting in perceptually based features and distance measures. As expected, search results closely correlate with human choices.

Original languageEnglish (US)
Pages189-194
Number of pages6
StatePublished - Jan 1 1999
EventProceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99 - Florence, Italy
Duration: Jun 7 1999Jun 11 1999

Other

OtherProceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99
CityFlorence, Italy
Period6/7/996/11/99

Fingerprint

Color
Textures
Image understanding
Pattern matching
Image retrieval
Processing

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Cite this

Mojsilovic, A., Kovacevic, J., Hu, J., Safranek, R. J., & Ganapathy, S. K. (1999). Matching and retrieval based on the vocabulary and grammar of color patterns. 189-194. Paper presented at Proceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99, Florence, Italy, .

Matching and retrieval based on the vocabulary and grammar of color patterns. / Mojsilovic, A.; Kovacevic, Jelena; Hu, J.; Safranek, R. J.; Ganapathy, S. K.

1999. 189-194 Paper presented at Proceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99, Florence, Italy, .

Research output: Contribution to conferencePaper

Mojsilovic, A, Kovacevic, J, Hu, J, Safranek, RJ & Ganapathy, SK 1999, 'Matching and retrieval based on the vocabulary and grammar of color patterns' Paper presented at Proceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99, Florence, Italy, 6/7/99 - 6/11/99, pp. 189-194.
Mojsilovic A, Kovacevic J, Hu J, Safranek RJ, Ganapathy SK. Matching and retrieval based on the vocabulary and grammar of color patterns. 1999. Paper presented at Proceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99, Florence, Italy, .
Mojsilovic, A. ; Kovacevic, Jelena ; Hu, J. ; Safranek, R. J. ; Ganapathy, S. K. / Matching and retrieval based on the vocabulary and grammar of color patterns. Paper presented at Proceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99, Florence, Italy, .6 p.
@conference{3deaccf05266486e8cdcfa17bf2ea7b6,
title = "Matching and retrieval based on the vocabulary and grammar of color patterns",
abstract = "While it is recognized that images are described through color, texture and shapes of objects in the scene, the general image understanding is still difficult. Thus, to perform image retrieval in a human-like manner one has to chose a specific domain, understand how users achieve similarity within that domain and then build a system that duplicates human performance. Since color and texture are fundamental aspects of human perception we propose a set of techniques for retrieval of color patterns. To determine how humans judge similarity of color patterns we performed a subjective study. Based on the results of the study five most relevant visual categories for the perception of pattern similarity were identified. We also determined the hierarchy of rules governing the use of these categories. Based on these results we designed a system which accepts one or more texture images as input, and depending on the query, produces a set of choices that follow human behavior in pattern matching. Processing steps in our model follow those of the human visual system, resulting in perceptually based features and distance measures. As expected, search results closely correlate with human choices.",
author = "A. Mojsilovic and Jelena Kovacevic and J. Hu and Safranek, {R. J.} and Ganapathy, {S. K.}",
year = "1999",
month = "1",
day = "1",
language = "English (US)",
pages = "189--194",
note = "Proceedings of the 1999 6th International Conference on Multimedia Computing and Systems - IEEE ICMCS'99 ; Conference date: 07-06-1999 Through 11-06-1999",

}

TY - CONF

T1 - Matching and retrieval based on the vocabulary and grammar of color patterns

AU - Mojsilovic, A.

AU - Kovacevic, Jelena

AU - Hu, J.

AU - Safranek, R. J.

AU - Ganapathy, S. K.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - While it is recognized that images are described through color, texture and shapes of objects in the scene, the general image understanding is still difficult. Thus, to perform image retrieval in a human-like manner one has to chose a specific domain, understand how users achieve similarity within that domain and then build a system that duplicates human performance. Since color and texture are fundamental aspects of human perception we propose a set of techniques for retrieval of color patterns. To determine how humans judge similarity of color patterns we performed a subjective study. Based on the results of the study five most relevant visual categories for the perception of pattern similarity were identified. We also determined the hierarchy of rules governing the use of these categories. Based on these results we designed a system which accepts one or more texture images as input, and depending on the query, produces a set of choices that follow human behavior in pattern matching. Processing steps in our model follow those of the human visual system, resulting in perceptually based features and distance measures. As expected, search results closely correlate with human choices.

AB - While it is recognized that images are described through color, texture and shapes of objects in the scene, the general image understanding is still difficult. Thus, to perform image retrieval in a human-like manner one has to chose a specific domain, understand how users achieve similarity within that domain and then build a system that duplicates human performance. Since color and texture are fundamental aspects of human perception we propose a set of techniques for retrieval of color patterns. To determine how humans judge similarity of color patterns we performed a subjective study. Based on the results of the study five most relevant visual categories for the perception of pattern similarity were identified. We also determined the hierarchy of rules governing the use of these categories. Based on these results we designed a system which accepts one or more texture images as input, and depending on the query, produces a set of choices that follow human behavior in pattern matching. Processing steps in our model follow those of the human visual system, resulting in perceptually based features and distance measures. As expected, search results closely correlate with human choices.

UR - http://www.scopus.com/inward/record.url?scp=0032642582&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032642582&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0032642582

SP - 189

EP - 194

ER -