• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2019 Fiscal Year Final Research Report

Vector Image Retrieval Considering the Similarity of Essential Parts of Images

Research Project

  • PDF
Project/Area Number 17K00153
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Multimedia database
Research InstitutionKansai University (2018-2019)
Niigata University (2017)

Principal Investigator

Hayashi Takahiro  関西大学, 総合情報学部, 教授 (60342490)

Project Period (FY) 2017-04-01 – 2020-03-31
Keywordsベクタ画像 / 画像検索 / 情報検索
Outline of Final Research Achievements

To develop a vector image retrieval system considering on the similarity of essential parts of images, the following subjects were investigated. (1) Gestalt grouping principles were computationally modeled for extracting essential parts from a vector image. (2) A raster-to-vector image conversion algorithm was developed and experimentally evaluated. (3) An algorithm for evaluating the similarity between a pair of essentail parts in vector images was developed and experimentally evaluated. (4) A fast algorithm for similarity retrieval of vector images was developed and experimentally evaluated.

Free Research Field

マルチメディア・データベース

Academic Significance and Societal Importance of the Research Achievements

ベクタ画像は、画像内部に存在する個々の図形オブジェクトごとに構造情報が独立して記録される画像形式であり近年利用が急増している。一方で,ベクタ画像を対象とした類似検索の研究開発は研究開発の途上にあり、特に、要部観察に基づく類似ベクタ画像検索についてはその効果は確認されていなかった。本研究はこの点に着目し、要部観察に基づく類似検索の仕組みをベクタ画像の検索へと応用した点が意義がある。

URL: 

Published: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi