Retrieval of 2D vector images by matching weighted feature points

Takahiro Hayashi, Tatsuya Kiyono, Koji Abe, Rikio Onai

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

5 Citations (Scopus)

Abstract

A novel method for content-based 2D vector image retrieval is proposed in this paper. To retrieve vector images, first, the proposed method extracts WFPs (Weighted Feature Points) from vector images. In this extraction process, the method directly accesses the parameters of Bezier curves defining the shapes of vector images and computes WFPs of the images according to these parameters. Second, to a pair of vector images, the method evaluates similarity by matching WFPs using PTD (Proportional Transfer Distance). In the proposed method, vector images are not rasterized, which enables real-time retrieval. As a prototyping, we have implemented a system for sketch-based vector image retrieval. In the system, a sketch is used as a query. To bridge the representation gap between sketches and vector images in a database, the strokes in sketches are approximated with Bezier curves as a preprocess. Using the system and a database containing 1,120 logomarks, we have confirmed the retrieval performance and have discussed the limits of the proposed method.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings
Pages961-964
Number of pages4
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE International Conference on Image Processing, ICIP 2008 - San Diego, CA
Duration: 2008 Oct 122008 Oct 15

Other

Other2008 IEEE International Conference on Image Processing, ICIP 2008
CitySan Diego, CA
Period08/10/1208/10/15

Fingerprint

Image retrieval

Keywords

  • Bezier curves
  • Content-based image retrieval
  • Feature points
  • Query-by-sketch
  • Vector images

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Hayashi, T., Kiyono, T., Abe, K., & Onai, R. (2008). Retrieval of 2D vector images by matching weighted feature points. In 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings (pp. 961-964). [4711916] https://doi.org/10.1109/ICIP.2008.4711916

Retrieval of 2D vector images by matching weighted feature points. / Hayashi, Takahiro; Kiyono, Tatsuya; Abe, Koji; Onai, Rikio.

2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings. 2008. p. 961-964 4711916.

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

Hayashi, T, Kiyono, T, Abe, K & Onai, R 2008, Retrieval of 2D vector images by matching weighted feature points. in 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings., 4711916, pp. 961-964, 2008 IEEE International Conference on Image Processing, ICIP 2008, San Diego, CA, 08/10/12. https://doi.org/10.1109/ICIP.2008.4711916
Hayashi T, Kiyono T, Abe K, Onai R. Retrieval of 2D vector images by matching weighted feature points. In 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings. 2008. p. 961-964. 4711916 https://doi.org/10.1109/ICIP.2008.4711916
Hayashi, Takahiro ; Kiyono, Tatsuya ; Abe, Koji ; Onai, Rikio. / Retrieval of 2D vector images by matching weighted feature points. 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings. 2008. pp. 961-964
@inproceedings{4d1777a7671a4e15895c0fba9bba060e,
title = "Retrieval of 2D vector images by matching weighted feature points",
abstract = "A novel method for content-based 2D vector image retrieval is proposed in this paper. To retrieve vector images, first, the proposed method extracts WFPs (Weighted Feature Points) from vector images. In this extraction process, the method directly accesses the parameters of Bezier curves defining the shapes of vector images and computes WFPs of the images according to these parameters. Second, to a pair of vector images, the method evaluates similarity by matching WFPs using PTD (Proportional Transfer Distance). In the proposed method, vector images are not rasterized, which enables real-time retrieval. As a prototyping, we have implemented a system for sketch-based vector image retrieval. In the system, a sketch is used as a query. To bridge the representation gap between sketches and vector images in a database, the strokes in sketches are approximated with Bezier curves as a preprocess. Using the system and a database containing 1,120 logomarks, we have confirmed the retrieval performance and have discussed the limits of the proposed method.",
keywords = "Bezier curves, Content-based image retrieval, Feature points, Query-by-sketch, Vector images",
author = "Takahiro Hayashi and Tatsuya Kiyono and Koji Abe and Rikio Onai",
year = "2008",
doi = "10.1109/ICIP.2008.4711916",
language = "English",
isbn = "1424417643",
pages = "961--964",
booktitle = "2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings",

}

TY - GEN

T1 - Retrieval of 2D vector images by matching weighted feature points

AU - Hayashi, Takahiro

AU - Kiyono, Tatsuya

AU - Abe, Koji

AU - Onai, Rikio

PY - 2008

Y1 - 2008

N2 - A novel method for content-based 2D vector image retrieval is proposed in this paper. To retrieve vector images, first, the proposed method extracts WFPs (Weighted Feature Points) from vector images. In this extraction process, the method directly accesses the parameters of Bezier curves defining the shapes of vector images and computes WFPs of the images according to these parameters. Second, to a pair of vector images, the method evaluates similarity by matching WFPs using PTD (Proportional Transfer Distance). In the proposed method, vector images are not rasterized, which enables real-time retrieval. As a prototyping, we have implemented a system for sketch-based vector image retrieval. In the system, a sketch is used as a query. To bridge the representation gap between sketches and vector images in a database, the strokes in sketches are approximated with Bezier curves as a preprocess. Using the system and a database containing 1,120 logomarks, we have confirmed the retrieval performance and have discussed the limits of the proposed method.

AB - A novel method for content-based 2D vector image retrieval is proposed in this paper. To retrieve vector images, first, the proposed method extracts WFPs (Weighted Feature Points) from vector images. In this extraction process, the method directly accesses the parameters of Bezier curves defining the shapes of vector images and computes WFPs of the images according to these parameters. Second, to a pair of vector images, the method evaluates similarity by matching WFPs using PTD (Proportional Transfer Distance). In the proposed method, vector images are not rasterized, which enables real-time retrieval. As a prototyping, we have implemented a system for sketch-based vector image retrieval. In the system, a sketch is used as a query. To bridge the representation gap between sketches and vector images in a database, the strokes in sketches are approximated with Bezier curves as a preprocess. Using the system and a database containing 1,120 logomarks, we have confirmed the retrieval performance and have discussed the limits of the proposed method.

KW - Bezier curves

KW - Content-based image retrieval

KW - Feature points

KW - Query-by-sketch

KW - Vector images

UR - http://www.scopus.com/inward/record.url?scp=69949174826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69949174826&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2008.4711916

DO - 10.1109/ICIP.2008.4711916

M3 - Conference contribution

SN - 1424417643

SN - 9781424417643

SP - 961

EP - 964

BT - 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings

ER -