Converting SVG images to text and speech

Abstract

There are contents with a strong visual component, e.g.,in the engineering field, such as technical drawings,charts, diagrams, etc., virtually inaccessible for peoplewith visual disabilities (blind, visually impaired, etc.).These contents are mostly vector based and can generallybe found on the Web in various formats, but therecommended one is SVG.The authors created an online application to convertSVG images (containing simple geometric figures ofvarious sizes, filling colours and thickness and colourfilling contours) in textual and spoken description by aspeech synthesizer, client side based, without browserplugins. This application also allows the user to navigatewith efficiency through the image description using fourlevels of detail and keyboard commands.In this paper, the authors propose a novel method forimage description based on the Gestalt theory,considering the cognitive load and, for the first time,providing users with visual impairments access to the fullcontent of SVG images.Application tests were carried out with 11 users (eightnormally sighted, two blind and one amblyopic),comparing descriptions made by the application and byhumans. The authors concluded that, for all users, therewere improvements of 9%, using the application.Considering only the visually impaired, this figure risesto 18%.