Improvement of Page Segmentation Model for Analytics of Handwritten Notes

• Item type: SIG Technical Reports(1)
• 公開日: 2022-06-04
• タイトル: Improvement of Page Segmentation Model for Analytics of Handwritten Notes
• タイトル / 言語: en
• タイトル: Improvement of Page Segmentation Model for Analytics of Handwritten Notes
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: セッション3
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Kyushu University
• 著者所属: Kyushu University
• 著者所属: Kyushu University
• 著者所属(英): en
• 著者所属(英): Kyushu University
• 著者所属(英): en
• 著者所属(英): Kyushu University
• 著者所属(英): en
• 著者所属(英): Kyushu University
• 著者名: Yunyu, Zhou; Tsubasa, Minematsu; Atsushi, Shimada
• 著者名(英): Yunyu, Zhou; Tsubasa, Minematsu; Atsushi, Shimada
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Student's handwritten notes contain text, formula, graph. In our previous study, we used the U-Net model and post-processing to segment handwritten notes and used the segmentation results to analyze students' learning behavior. In this paper, we use the improved U-Net model to complete page segmentation, and in the case of not using Post Processing, the performance of this model is close to what we have used before, also use the obtained experimental results to analyze the students' learning behavior. On the other hand, the analyze of the mutual promotion effect of the two tasks in the multi-task model is reported.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Student's handwritten notes contain text, formula, graph. In our previous study, we used the U-Net model and post-processing to segment handwritten notes and used the segmentation results to analyze students' learning behavior. In this paper, we use the improved U-Net model to complete page segmentation, and in the case of not using Post Processing, the performance of this model is close to what we have used before, also use the obtained experimental results to analyze the students' learning behavior. On the other hand, the analyze of the mutual promotion effect of the two tasks in the multi-task model is reported.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12496725
• 書誌情報: 研究報告教育学習支援情報システム（CLE）; 巻 2022-CLE-37, 号 10, p. 1-6, 発行日 2022-06-04
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8620
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会