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

Image Reconstruction from Bag of Visual Words using Large-scale Image Data

Research Project

Project/Area Number 26540079
Research Category

Grant-in-Aid for Challenging Exploratory Research

Allocation TypeMulti-year Fund
Research Field Perceptual information processing
Research InstitutionThe University of Tokyo

Principal Investigator

Harada Tatsuya  東京大学, 情報理工学(系)研究科, 教授 (60345113)

Project Period (FY) 2014-04-01 – 2016-03-31
Project Status Completed (Fiscal Year 2015)
Budget Amount *help
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2015: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywordsコンピュータビジョン / 機械学習 / 画像復元 / 画像認識 / 人工知能
Outline of Final Research Achievements

The objective of this study is to reconstruct images from Bag-of-Visual-Words (BoVW). BoVW is defined here as a histogram of quantized local descriptors extracted densely on a regular grid at a single scale. This task is challenging for two reasons: 1) BoVW includes quantization errors. 2) BoVW lacks spatial information of local descriptors. To tackle this difficult task, we use a large-scale image database to estimate the spatial arrangement of local descriptors. Then this task creates a jigsaw puzzle problem with adjacency and global location costs of visual words. Solving this optimization problem is also challenging because it is known as an NP-Hard problem. We propose a heuristic but efficient method to optimize it. To underscore the effectiveness of our method, we apply it to BoVWs extracted from about 100 different categories and demonstrate that it can reconstruct the original images.

Report

(3 results)
  • 2015 Annual Research Report   Final Research Report ( PDF )
  • 2014 Research-status Report
  • Research Products

    (6 results)

All 2015 2014 Other

All Journal Article (4 results) (of which Peer Reviewed: 2 results,  Open Access: 2 results) Remarks (2 results)

  • [Journal Article] 画像識別と画像復元2015

    • Author(s)
      原田達也
    • Journal Title

      情報処理

      Volume: 56(7) Pages: 640-645

    • Related Report
      2015 Annual Research Report
  • [Journal Article] Image Reconstruction from Bag-of-Visual-Words2015

    • Author(s)
      Hiroharu Kato and Tatsuya Harada
    • Journal Title

      arXiv preprint

      Volume: arXiv:1505.05190

    • Related Report
      2015 Annual Research Report
  • [Journal Article] Image Reconstruction from Bag-of-Visual-Words2014

    • Author(s)
      Hiroharu Kato, Tatsuya Harada
    • Journal Title

      The Twenty-Seventh IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2014)

      Volume: 1 Pages: 955-962

    • DOI

      10.1109/cvpr.2014.127

    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Automatic Image Synthesis from Keywords Using Scene Context2014

    • Author(s)
      Sho Inaba, Asako Kanezaki, Tatsuya Harada
    • Journal Title

      the 22th Annual ACM International Conference on Multimedia (ACMMM 2014)

      Volume: 1 Pages: 1149-1152

    • DOI

      10.1145/2647868.2655009

    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Open Access
  • [Remarks] Image Generation

    • URL

      http://www.mi.t.u-tokyo.ac.jp/#researchdetail-generation

    • Related Report
      2015 Annual Research Report
  • [Remarks]

    • URL

      http://www.mi.t.u-tokyo.ac.jp/#publication

    • Related Report
      2014 Research-status Report

URL: 

Published: 2014-04-04   Modified: 2017-05-10  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi