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

Generating Saliency Map for Images with Leading Lines

Research Project

Project/Area Number 16K12459
Research Category

Grant-in-Aid for Challenging Exploratory Research

Allocation TypeMulti-year Fund
Research Field Perceptual information processing
Research InstitutionUniversity of Yamanashi

Principal Investigator

MAO xiaoyang  山梨大学, 大学院総合研究部, 教授 (20283195)

Co-Investigator(Kenkyū-buntansha) 藤代 一成  慶應義塾大学, 理工学部(矢上), 教授 (00181347)
豊浦 正広  山梨大学, 大学院総合研究部, 准教授 (80550780)
Research Collaborator GYOBA Jiro  東北大学, 文学研究科, 教授 (50142899)
Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywords顕著性マップ
Outline of Final Research Achievements

Researchers have proposed a wide variety of saliency models,ranging from models that use local,low-level image features to recent approaches that incorporate semantic information and deep learning. However, these models do not account for the visual attention related to certain global structures evident in images. We focused specifically on “leading-line” structures,in which lines converge on a single point.We have conducted the experiments to investigate the visual attentions in images with leading line structure and proposed a new saliency model combining the low level feature of center-surrounding differences of visual stimuli, the semantic feature of center-bias and the structure feature of leading lines. Experimental results show that our model outperforms the existing models with all the representative evaluation metrics of saliency map for the images with leading line structures.

Academic Significance and Societal Importance of the Research Achievements

画像提示の初期段階における人間の注意を予測する顕著性マップはロボットビジョンや広告デザインをはじめ,様々な分野で注目されている.局所的な低レベルの画像特徴を利用したモデルに加え,近年では意味論的な情報を考慮したものやDeep Learning を利用したものなど,様々な顕著性モデルが提案された.一方で,これらのモデルは画像内に存在する大域的な構造による誘目効果を考慮していないなかった.本研究の成果はロボットビジョン,広告デザイン,画像編集などへの応用が期待できるのみでなく,認知心理学分野においても多くの後続研究を誘発するポテンシャルの高さを有している.

Report

(4 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (17 results)

All 2018 2017 2016 Other

All Int'l Joint Research (2 results) Journal Article (7 results) (of which Int'l Joint Research: 2 results,  Peer Reviewed: 6 results,  Open Access: 2 results) Presentation (7 results) (of which Int'l Joint Research: 2 results) Remarks (1 results)

  • [Int'l Joint Research] 杭州電子科技大学(中国)

    • Related Report
      2018 Annual Research Report
  • [Int'l Joint Research] 杭州電子科技大学/浙江大学(中国)

    • Related Report
      2017 Research-status Report
  • [Journal Article] A cascaded algorithm for image quality assessment and image denoising based on CNN for image security and authorization2018

    • Author(s)
      Janjun Li, Jie Yu, Lanlan Xu, Xinying Xue, Chin-Chen Chang, Xiaoyang Mao, Junfeng Hu
    • Journal Title

      Security and Communication Networks

      Volume: 2018 Pages: 1-13

    • DOI

      10.1155/2018/8176984

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Visual saliency prediction for images with leading line structure2018

    • Author(s)
      Issei Mochizuki, Masahiro Toyoura, Xiaoyang Mao
    • Journal Title

      The Visual Computer

      Volume: 34(6-8) Issue: 6-8 Pages: 1031-1041

    • DOI

      10.1007/s00371-018-1518-6

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Suggesting the Appropriate Number of Observers for Predicting Video Saliency with Eye-Tracking Data2018

    • Author(s)
      Chuancai Li, Jiayi Xu, Jianjun Li, Xiaoyang Mao
    • Journal Title

      Proceedings of Computer Graphics International 2018

      Volume: 2018 Pages: 1-5

    • DOI

      10.1145/3208159.3208193

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] リーディングラインを考慮した顕著性マップの拡張2017

    • Author(s)
      望月 一生,豊浦 正広,茅 暁陽
    • Journal Title

      Visual Computing/グラフィクスとCAD合同シンポジウム

      Volume: 1

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] Auto-framing based on user camera movemen2017

    • Author(s)
      Tomoya Sawada, Masahiro Toyoura, Xiaoyang Mao
    • Journal Title

      CGI '17 Proceedings of the Computer Graphics International Conference

      Volume: 1 Pages: 1-6

    • DOI

      10.1145/3095140.3095158

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] Scene-Aware Style Transferring Using GIST2017

    • Author(s)
      Toyoura M., Abe N., Mao X
    • Journal Title

      Transactions on Computational Science XXX. Lecture Notes in Computer Science

      Volume: 10560 Pages: 29-49

    • DOI

      10.1007/978-3-662-56006-8_3

    • ISBN
      9783662560051, 9783662560068
    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Improving Eye Tracking Accuracy by Head Motion History2017

    • Author(s)
      Masahiro Toyoura, Takumi Tanaka, Atsushi Sugiura, Xiaoyang Mao
    • Journal Title

      IIEEJ Transactions on Image Electronics and Visual Computing

      Volume: 5 Pages: 92-98

    • NAID

      130007402239

    • Related Report
      2017 Research-status Report
  • [Presentation] 熟練教師の注視を再現する全周授業映像提示2018

    • Author(s)
      豊浦 正広,川村 由基生,西口 敏司,茅 暁陽,村上 正行
    • Organizer
      日本教育工学会 全国大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] LinDA:漫画背景画像の半自動生成に向けた線分特徴量抽出と分類2018

    • Author(s)
      野村芽久美,中山雅紀,藤代一成
    • Organizer
      映像表現・芸術科学フォーラム2019
    • Related Report
      2018 Annual Research Report
  • [Presentation] LinDA:漫画背景画像の半自動生成に向けた線分特徴量抽出2018

    • Author(s)
      野村芽久美,中山雅紀,藤代一成
    • Organizer
      情報処理学会第81回
    • Related Report
      2018 Annual Research Report
  • [Presentation] Auto Framing Based on User’s Camera Movement2017

    • Author(s)
      Tomoya Sawada, Masahiro Toyoura, Xiaoyang Mao
    • Organizer
      Computer Graphics International
    • Place of Presentation
      Keio University, Yokohama, Japan
    • Year and Date
      2017-06-27
    • Related Report
      2016 Research-status Report
  • [Presentation] リーディングラインを考慮した顕著性マップの拡張2017

    • Author(s)
      望月 一生, 豊浦 正広, 茅 暁陽
    • Organizer
      Visual Computing/グラフィクスとCAD合同シンポジウム
    • Place of Presentation
      一橋講堂,東京
    • Year and Date
      2017-06-23
    • Related Report
      2016 Research-status Report
  • [Presentation] Eye Tracking by Head Motion History2017

    • Author(s)
      Masahiro Toyoura, Takumi Tanaka, Atsushi Sugiura, Xiaoyang Mao
    • Organizer
      International Workshop on Image Electronics and Visual Computing
    • Place of Presentation
      Danang, Vietnam
    • Year and Date
      2017-03-01
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] Painterly Image Generation Using Scene-Aware Style Transferring2016

    • Author(s)
      Masahiro Toyoura, Noriyuki Abe, Xiaoyang Mao
    • Organizer
      Cyberworlds
    • Place of Presentation
      Chongqing, China
    • Year and Date
      2016-09-28
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Remarks]

    • URL

      http://www.vc.media.yamanashi.ac.jp/

    • Related Report
      2016 Research-status Report

URL: 

Published: 2016-04-21   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi