Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ACCSAMS: Automatic Conversion of Exam Documents to Accessible Learning Material for Blind and Visually Impaired

David Wilkening, Omar Moured, Thorsten Schwarz, Karin Muller, Rainer Stiefelhagen

TL;DR

The paper addresses the barrier of unreachable exam materials for blind and visually impaired students by introducing ACCSAMS, a semi-automatic pipeline that transforms exams into accessible formats. It combines layout segmentation using YOLOv8, hierarchy extraction, and solution detection with a user-facing interface to verify and export results, supported by a multilingual dataset of 1,293 German and 900 English exams collected from Common Crawl. The authors provide a thorough evaluation of content-block detection, read-order and hierarchy accuracy, and a user study that reports a SUS of 84, indicating strong usability. The work demonstrates practical impact by enabling efficient production of accessible study materials and sets the stage for automatic alt-text and editor enhancements in future iterations, improving accessibility for BVI learners in exam contexts.

Abstract

Exam documents are essential educational materials for exam preparation. However, they pose a significant academic barrier for blind and visually impaired students, as they are often created without accessibility considerations. Typically, these documents are incompatible with screen readers, contain excessive white space, and lack alternative text for visual elements. This situation frequently requires intervention by experienced sighted individuals to modify the format and content for accessibility. We propose ACCSAMS, a semi-automatic system designed to enhance the accessibility of exam documents. Our system offers three key contributions: (1) creating an accessible layout and removing unnecessary white space, (2) adding navigational structures, and (3) incorporating alternative text for visual elements that were previously missing. Additionally, we present the first multilingual manually annotated dataset, comprising 1,293 German and 900 English exam documents which could serve as a good training source for deep learning models.

ACCSAMS: Automatic Conversion of Exam Documents to Accessible Learning Material for Blind and Visually Impaired

TL;DR

The paper addresses the barrier of unreachable exam materials for blind and visually impaired students by introducing ACCSAMS, a semi-automatic pipeline that transforms exams into accessible formats. It combines layout segmentation using YOLOv8, hierarchy extraction, and solution detection with a user-facing interface to verify and export results, supported by a multilingual dataset of 1,293 German and 900 English exams collected from Common Crawl. The authors provide a thorough evaluation of content-block detection, read-order and hierarchy accuracy, and a user study that reports a SUS of 84, indicating strong usability. The work demonstrates practical impact by enabling efficient production of accessible study materials and sets the stage for automatic alt-text and editor enhancements in future iterations, improving accessibility for BVI learners in exam contexts.

Abstract

Exam documents are essential educational materials for exam preparation. However, they pose a significant academic barrier for blind and visually impaired students, as they are often created without accessibility considerations. Typically, these documents are incompatible with screen readers, contain excessive white space, and lack alternative text for visual elements. This situation frequently requires intervention by experienced sighted individuals to modify the format and content for accessibility. We propose ACCSAMS, a semi-automatic system designed to enhance the accessibility of exam documents. Our system offers three key contributions: (1) creating an accessible layout and removing unnecessary white space, (2) adding navigational structures, and (3) incorporating alternative text for visual elements that were previously missing. Additionally, we present the first multilingual manually annotated dataset, comprising 1,293 German and 900 English exam documents which could serve as a good training source for deep learning models.
Paper Structure (21 sections, 1 figure, 1 table)

This paper contains 21 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Need-finding Interviews
  4. Participants
  5. Procedure
  6. Findings
  7. Creation of the Exam Documents Dataset
  8. The ACCSAMS System
  9. Layout segmentation
  10. Hierarchy Extraction
  11. Solution detection
  12. User Interface
  13. Evaluation
  14. System Evaluation
  15. User Study of User Interface
  16. ...and 6 more sections

Figures (1)

  • Figure 1: The ACCSAMS pipeline: (a) Exam page. (b) Automated processing (c) User application of corrections and repositioning of solutions (d) Output to accessible markdown or conversion to WORD format.