Alt4Blind: A User Interface to Simplify Charts Alt-Text Creation

TL;DR

Alt4Blind introduces a retrieval-based system and user interface to assist in creating accurate and accessible alt-texts for charts, addressing limitations of existing AI models by providing high-quality references.

Contribution

The paper presents a new benchmark dataset, a deep learning retrieval model, and a user interface to improve alt-text creation for charts.

Findings

High-quality dataset of 5,000 chart images and alt-texts

Effective deep learning model for retrieving similar charts

User interface shown to be usable in preliminary studies

Abstract

Alternative Texts (Alt-Text) for chart images are essential for making graphics accessible to people with blindness and visual impairments. Traditionally, Alt-Text is manually written by authors but often encounters issues such as oversimplification or complication. Recent trends have seen the use of AI for Alt-Text generation. However, existing models are susceptible to producing inaccurate or misleading information. We address this challenge by retrieving high-quality alt-texts from similar chart images, serving as a reference for the user when creating alt-texts. Our three contributions are as follows: (1) we introduce a new benchmark comprising 5,000 real images with semantically labeled high-quality Alt-Texts, collected from Human Computer Interaction venues. (2) We developed a deep learning-based model to rank and retrieve similar chart images that share the same visual and textual semantics. (3) We designed a user interface (UI) to facilitate the alt-text creation process. Our preliminary interviews and investigations highlight the usability of our UI. For the dataset and further details, please refer to our project page: https://moured.github.io/alt4blind/.