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

A study of image processing methods to improve explainability and redesign through shallow layer learning

Research Project

Project/Area Number 20K11865
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionTottori University

Principal Investigator

Iwai Yoshio  鳥取大学, 工学研究科, 教授 (70294163)

Co-Investigator(Kenkyū-buntansha) 西山 正志  鳥取大学, 工学研究科, 教授 (20756449)
Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Keywords浅層学習 / 説明可能性 / 再設計可能性 / 機械学習 / 画像認識 / ランダムプロジェクション / 再設計性 / 画像処理 / パターン認識
Outline of Research at the Start

本研究では,深層学習が持つ一体化学習という特徴を維持しつつ,深いネットワーク構造を取り払い,浅いネットワーク構造で機械学習を行うことで,学習結果の説明可能性を向上させつつ,再設計の容易な画像認識手法を実現することを目的とする.本研究により,高い識別性能を実現するための方法論として,深いネットワーク構造だけでなく,再設計可能な浅いネットワーク構造による高い学習容量を持つ識別器と認識性能に寄与する学習可能な特徴抽出器により,十分な性能を発揮できることを実験的に示す.

Outline of Final Research Achievements

The purpose of this study is to realize an image recognition method that can be easily redesigned while improving the explainability of the learning results by removing the deep network structure and performing machine learning with a shallow network structure, while maintaining the feature of integrated learning that deep learning possesses. In particular, to improve the explainability and redesignability, it is necessary to replace the feature extraction process with a conventional feature extraction process using a deep network structure, which is realized by deep learning. Therefore, we extended the conventional feature extraction process and constructed a learnable feature extractor by parameterizing it, and built a prototype discriminator with a high learning capacity based on a redesignable shallow network structure and a learnable feature extractor that contributes to recognition performance.

Academic Significance and Societal Importance of the Research Achievements

本研究が実現することにより,計算機が何故そのような判断を下したかの説明を行いやすくなる.また,その説明を受けて,浅いネットワーク構造のため理解がしやすく,再設計を行うことが可能なネットワーク構造を構築することが出来る.

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (5 results)

All 2022 2021 2020

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (4 results) (of which Int'l Joint Research: 1 results,  Invited: 1 results)

  • [Journal Article] Foreground Detection in Outdoor Scenes by using Blind Gamma Correction and Layered Adaptive Background Models2020

    • Author(s)
      阪本 光翼、吉村 宏紀、西山 正志、岩井 儀雄
    • Journal Title

      電子情報通信学会論文誌D 情報・システム

      Volume: J103-D Issue: 10 Pages: 733-743

    • DOI

      10.14923/transinfj.2020IEP0005

    • ISSN
      1880-4535, 1881-0225
    • Year and Date
      2020-10-01
    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Diffusion Layered ABMを用いた背景差分における移動カメラの適用の検討2022

    • Author(s)
      眞柴 智, 西山 正志, 岩井 儀雄
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 非対称局所性保存射影とその応用2022

    • Author(s)
      岩井儀雄
    • Organizer
      第50回日本行動計量学会大会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] Beef marbling standard estimation for live cattle using multi-input convolutional neural network with ultrasound images2021

    • Author(s)
      Toshiki Katayama, Hirohumi Kawada, Masashi Nishiyama, Yoshio Iwai
    • Organizer
      15th International Conference on Quality Control by Artificial Vision
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] 背景画素拡散を用いた屋外背景差分法の精度向上の検討2021

    • Author(s)
      眞柴 智, 西山 正志, 岩井 儀雄
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2021 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi