Evaluation of Automated Image Descriptions for Visually Impaired Students

TL;DR

This study assesses automated image descriptions for visually impaired students, using expert interviews and questionnaires to evaluate template-based descriptions, highlighting their potential and identifying areas for improvement.

Contribution

It introduces a systematic evaluation method for automatic image descriptions tailored for visually impaired students, combining expert input and non-expert ratings.

Findings

Templates can generate useful descriptions

Questionnaire effectively identifies description problems

Potential for improving educational accessibility

Abstract

Illustrations are widely used in education, and sometimes, alternatives are not available for visually impaired students. Therefore, those students would benefit greatly from an automatic illustration description system, but only if those descriptions were complete, correct, and easily understandable using a screenreader. In this paper, we report on a study for the assessment of automated image descriptions. We interviewed experts to establish evaluation criteria, which we then used to create an evaluation questionnaire for sighted non-expert raters, and description templates. We used this questionnaire to evaluate the quality of descriptions which could be generated with a template-based automatic image describer. We present evidence that these templates have the potential to generate useful descriptions, and that the questionnaire identifies problems with description templates.