City Research Online

Abstract

One of the most pressing concerns in the field of adapted printed publications – that is, publications with additional supporting features to make them easily accessible by a wide variety of audiences – is preparing illustrations that can clearly convey visual information to the viewer. These illustrations need to be created while accounting for the needs of a diverse inclusive audience, whose requirements may be affected by disabilities such as visual impairment. Currently, there is a limited number of illustrators who can appropriately produce a large number of illustrations which satisfy these requirements; therefore, illustrating print publications is a time-consuming and expensive process for non-profit organizations which are responsible for their production. This article proposes a method for enhancing illustrations within print publications, given the source file (such as a PDF file) of a print publication. Based on modern text-to-image generators, this method extracts all illustrations from a print publication; converts them into textual prompts for a modern text-to-image generator; and finally, produces a series of adapted alternatives for each of the chosen illustrations based on the textual prompts. This allows publishers to obtain accessible illustrations for their publication in a manner of minutes, speeding up the adaptation process and enhancing its accessibility.

Publication Type:	Conference or Workshop Item (Paper)
Additional Information:	© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Publisher Keywords:	Accessible publishing, artificial intelligence, image synthesis, information technologies
Subjects:	P Language and Literature > PN Literature (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science Z Bibliography. Library Science. Information Resources
Departments:	School of Science & Technology School of Science & Technology > Computer Science School of Science & Technology > Computer Science > Software Reliability
SWORD Depositor:	Symplectic Administrator

Export

Downloads