2026-05-15T01:51:55Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00218272 2025-01-19T15:12:24Z 1164:6089:10878:10933

Improvement of Page Segmentation Model for Analytics of Handwritten Notes Improvement of Page Segmentation Model for Analytics of Handwritten Notes Yunyu, Zhou Tsubasa, Minematsu Atsushi, Shimada Yunyu, Zhou Tsubasa, Minematsu Atsushi, Shimada セッション3 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. 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. technical report 情報処理学会 2022-06-04 application/pdf 研究報告教育学習支援情報システム（CLE） 10 2022-CLE-37 1 6 2188-8620 AA12496725 https://ipsj.ixsq.nii.ac.jp/record/218272/files/IPSJ-CLE22037010.pdf eng