Spatial random partition for common visual pattern discovery

Junsong Yuan*, Ying Wu

*Corresponding author for this work

Research output: Contribution to conferencePaper

58 Citations (Scopus)

Abstract

Automatically discovering common visual patterns from a collection of images is an interesting but yet challenging task, in part because it is computationally prohibiting. Although representing images as visual documents based on discrete visual words offers advantages in computation, the performance of these word-based methods largely depends on the quality of the visual word dictionary. This paper presents a novel approach base on spatial random partition and fast word-free image matching. Represented as a set of continuous visual primitives, each image is randomly partitioned many times to form a pool of subimages. Each subimage is queried and matched against the pool, and then common patterns can be localized by aggregating the set of matched subimages. The asymptotic property and the complexity of the proposed method are given in this paper, along with many real experiments. Both theoretical studies and experiment results show its advantages.

Original languageEnglish (US)
DOIs
StatePublished - Dec 1 2007
Event2007 IEEE 11th International Conference on Computer Vision, ICCV - Rio de Janeiro, Brazil
Duration: Oct 14 2007Oct 21 2007

Other

Other2007 IEEE 11th International Conference on Computer Vision, ICCV
CountryBrazil
CityRio de Janeiro
Period10/14/0710/21/07

Fingerprint

Image matching
Glossaries
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Yuan, J., & Wu, Y. (2007). Spatial random partition for common visual pattern discovery. Paper presented at 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil. https://doi.org/10.1109/ICCV.2007.4408869
Yuan, Junsong ; Wu, Ying. / Spatial random partition for common visual pattern discovery. Paper presented at 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil.
@conference{e3add23439c24921acf1ae6765681e35,
title = "Spatial random partition for common visual pattern discovery",
abstract = "Automatically discovering common visual patterns from a collection of images is an interesting but yet challenging task, in part because it is computationally prohibiting. Although representing images as visual documents based on discrete visual words offers advantages in computation, the performance of these word-based methods largely depends on the quality of the visual word dictionary. This paper presents a novel approach base on spatial random partition and fast word-free image matching. Represented as a set of continuous visual primitives, each image is randomly partitioned many times to form a pool of subimages. Each subimage is queried and matched against the pool, and then common patterns can be localized by aggregating the set of matched subimages. The asymptotic property and the complexity of the proposed method are given in this paper, along with many real experiments. Both theoretical studies and experiment results show its advantages.",
author = "Junsong Yuan and Ying Wu",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICCV.2007.4408869",
language = "English (US)",
note = "2007 IEEE 11th International Conference on Computer Vision, ICCV ; Conference date: 14-10-2007 Through 21-10-2007",

}

Yuan, J & Wu, Y 2007, 'Spatial random partition for common visual pattern discovery' Paper presented at 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil, 10/14/07 - 10/21/07, . https://doi.org/10.1109/ICCV.2007.4408869

Spatial random partition for common visual pattern discovery. / Yuan, Junsong; Wu, Ying.

2007. Paper presented at 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Spatial random partition for common visual pattern discovery

AU - Yuan, Junsong

AU - Wu, Ying

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Automatically discovering common visual patterns from a collection of images is an interesting but yet challenging task, in part because it is computationally prohibiting. Although representing images as visual documents based on discrete visual words offers advantages in computation, the performance of these word-based methods largely depends on the quality of the visual word dictionary. This paper presents a novel approach base on spatial random partition and fast word-free image matching. Represented as a set of continuous visual primitives, each image is randomly partitioned many times to form a pool of subimages. Each subimage is queried and matched against the pool, and then common patterns can be localized by aggregating the set of matched subimages. The asymptotic property and the complexity of the proposed method are given in this paper, along with many real experiments. Both theoretical studies and experiment results show its advantages.

AB - Automatically discovering common visual patterns from a collection of images is an interesting but yet challenging task, in part because it is computationally prohibiting. Although representing images as visual documents based on discrete visual words offers advantages in computation, the performance of these word-based methods largely depends on the quality of the visual word dictionary. This paper presents a novel approach base on spatial random partition and fast word-free image matching. Represented as a set of continuous visual primitives, each image is randomly partitioned many times to form a pool of subimages. Each subimage is queried and matched against the pool, and then common patterns can be localized by aggregating the set of matched subimages. The asymptotic property and the complexity of the proposed method are given in this paper, along with many real experiments. Both theoretical studies and experiment results show its advantages.

UR - http://www.scopus.com/inward/record.url?scp=50649111840&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50649111840&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2007.4408869

DO - 10.1109/ICCV.2007.4408869

M3 - Paper

ER -

Yuan J, Wu Y. Spatial random partition for common visual pattern discovery. 2007. Paper presented at 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil. https://doi.org/10.1109/ICCV.2007.4408869