A Connected Components Based Layout Analysis Approach for Educational Documents

Liu, Ruiying, Yu, Shenbao, Yang, Fan, Pan, Yinghui and Zeng, Yifeng (2021) A Connected Components Based Layout Analysis Approach for Educational Documents. In: ICCSE 2021: IEEE: The 16th International Conference on Computer Science and Education. Proceedings of the International Conference on Computer Science & Education (ICCSE) . IEEE, Piscataway, pp. 875-880. ISBN 9781665447546, 9781665414685, 9781665414678

iccse.pdf - Accepted Version

Download (2MB) | Preview
Official URL: https://doi.org/10.1109/ICCSE51940.2021.9569699


Layout analysis, which aims to detect and categorize areas of interest on document images, is an increasingly important part in document image processing. Existing researches have conducted layout analysis on various documents, but none has been proposed for documents yielded from teaching, i.e. exam papers and workbooks, which are worth studying. In this paper, we propose a novel layout analysis system to achieve two tasks for workbook pages and exam papers respectively. On one hand, we segment text and non-text areas of workbook pages. On the other hand, we extract regions of interest on exam papers. Our system is based on connected component (CC) analysis, specifically, it extracts geometric features and spatial information of CCs to recognize page elements. We carried out experiments on images collected from real-world scenarios, and promising results confirmed the applicability and effectiveness of our system.

Item Type: Book Section
Additional Information: ICCSE 2021: The 16th International Conference on Computer Science and Education, Lancaster, 17-21 Aug 2021
Uncontrolled Keywords: Layout Analysis, Connected Component Analysis, Digital Image Processing
Subjects: G400 Computer Science
X900 Others in Education
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Related URLs:
Depositing User: John Coen
Date Deposited: 02 Jul 2021 12:56
Last Modified: 29 Oct 2021 13:30
URI: http://nrl.northumbria.ac.uk/id/eprint/46595

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics