• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2023 年度 実施状況報告書

画像情報処理による国境を越えた感情表現の解析

研究課題

研究課題/領域番号 23K16925
研究機関北陸先端科学技術大学院大学

研究代表者

SIRITANAWAN Prarinya  北陸先端科学技術大学院大学, 先端科学技術研究科, 助教 (20826383)

研究期間 (年度) 2023-04-01 – 2026-03-31
キーワードEmotional expression / Cross culture / Facial expression / Affective computing / Perception / Image processing / Computer vision
研究実績の概要

To understand the psychology of emotional expression in different cultures, we collected facial expression images from media in Japan and Thailand, created a cross-cultural facial expression dataset, and computationally demonstrated the differences in facial expressions of people from different cultures.
In addition, we further investigated the state-of-the-art facial expression recognition systems on our cross-cultural data and found the bias of these systems toward certain emotions of both Thai and Japanese samples. To confirm the bias of facial expression recognition in humans, we also conducted a subjective evaluation of human subjects' perception of these cross-cultural facial expression images.
For further use in deep learning-based emotional expression analysis, we also considered the generative models to synthesize facial expressions of emotion, as the number of images collected in our dataset is insufficient for deep learning-based methods. In addition to facial expression features, we have also explored the potential of using human gait features.
As part of our international collaboration efforts, we have also established our international collaboration with the researchers in Thailand through several meetings, including direct visits to Mahidol University (Faculty of Engineering and Department of Psychiatry, Faculty of Medicine, Siriraj Hospital) and Thammasat University. In addition, we organized the Special Session on Next Generation of Affective Computing (NGAC) at IEEE TENCON2023 to expand our domestic connection to more countries in Southeast Asia.

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

Research on cross-cultural analysis of emotional expressions, with a focus on facial expressions, has progressed well. We have published our work related to this research in 2 international journals, 3 international conference papers, and 2 presentations at the domestic workshop. In terms of international collaboration, we have established the relationship with the overseas researchers in Thailand, Vietnam, and Malaysia, with the potential to expand this collaboration in the future.

今後の研究の推進方策

We plan to collect more data for deep learning-based analysis with our international partner in Thailand, and to expand our sample space to other countries in Southeast Asia, such as Vietnam or Malaysia. We are also looking for a way to extend our work to other types of features that represent emotional expression, such as gait or posture.

次年度使用額が生じた理由

The cost of the computing server increased significantly due to the increase in the price of electronic equipment, exceeding the total of payable amount by this funding. Therefore, the purchase process was temporarily suspended. To alleviate the problem of computing resources, the principal investigator has changed his purchase plan to use the online cloud services or upgrade the existing computing server in his research unit in FY2024.

  • 研究成果

    (8件)

すべて 2024 2023

すべて 雑誌論文 (2件) (うち国際共著 2件、 査読あり 2件、 オープンアクセス 1件) 学会発表 (5件) (うち国際学会 3件) 学会・シンポジウム開催 (1件)

  • [雑誌論文] Multi-View Gait Analysis by Temporal Geometric Features of Human Body Parts2024

    • 著者名/発表者名
      Pattanapisont Thanyamon、Kotani Kazunori、Siritanawan Prarinya、Kondo Toshiaki、Karnjana Jessada
    • 雑誌名

      Journal of Imaging

      巻: 10 ページ: 88~88

    • DOI

      10.3390/jimaging10040088

    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] Compound facial expressions image generation for complex emotions2023

    • 著者名/発表者名
      Win Shwe Sin Khine、Siritanawan Prarinya、Kotani Kazunori
    • 雑誌名

      Multimedia Tools and Applications

      巻: 82 ページ: 11549~11588

    • DOI

      10.1007/s11042-022-14289-7

    • 査読あり / 国際共著
  • [学会発表] Gait image analysis by the voting method on the body parts feature2024

    • 著者名/発表者名
      Thanyamon Pattanapisont, Kazunori Kotani, Prarinya Siritanawan
    • 学会等名
      画像電子学会 第307回研究会
  • [学会発表] Exploring the Cultural Gaps in Facial Expression Recognition Systems by Visual Features2023

    • 著者名/発表者名
      Prarinya Siritanawan, Haruyuki Kojima, Kazunori Kotani
    • 学会等名
      IEEE TENCON2023
    • 国際学会
  • [学会発表] Facial Expression Analysis Interpreting Emotion in Multicultural Settings2023

    • 著者名/発表者名
      Prarinya Siritanawan, Attawit Chaiyaroj, Poraneepan Tantawanich, Kittikhun Sirinaksomboon, Kazunori Kotani
    • 学会等名
      Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE2023)
    • 国際学会
  • [学会発表] Gait Image Analysis Based on Human Body Parts Model2023

    • 著者名/発表者名
      Thanyamon Pattanapisont, Prarinya Siritanawan, Kazunori Kotani, Toshiaki Kondo, Jessada Karnjana
    • 学会等名
      IEEE International Conference on Agents (ICA)
    • 国際学会
  • [学会発表] Gait Recognition by the Voting Method on Temporal Geometric Features of Human Body Parts2023

    • 著者名/発表者名
      Thanyamon Pattanapisont, Prarinya Siritanawan, Kazunori Kotani
    • 学会等名
      2023年映像メディア処理シンポジウム(PCSJ/IMPS2023), 2023年11月
  • [学会・シンポジウム開催] Special Session on Next Generation of Affective Computing (NGAC) at the IEEE TENCON20232023

URL: 

公開日: 2024-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi