Web-Adapted Supervised Segmentation to Improve a New Tactile Vision Sensory Substitution (TVSS) Technology

Nowadays, hand-held devices are being used more and more, especially for web navigation. But the small screen size of these devices requires adapting web page contents to be browsed more conveniently. A fundamental step in a successful automatic adaptation process of a web page is perception its visual layout and mining its Document Object Model (DOM) structure. In this paper, we present a new web-adapted supervised segmentation algorithm dedicated to vibro-tactile access on touch-screen devices. This suggested algorithm is fundamental in our framework whose aim is enhancing the ability of Visually Impaired Persons (VIP) to understand the 2-dimension web page layout by converting web pages into vibrating pages using a graphical vibro-tactile language. A comparison between automatic and manual segmented pages is presented. The objectives of this comparison are, on the one hand, to know how users understand web page layout structure based on their visual perception, and on the other hand, to explore the main differences between automatic and manual segmentation.