An experimental system for auditory image representations

Abstract

This paper presents an experimental system for the conversion of images into sound patterns. The system was designed to provide auditory image representations within some of the known limitations of the human hearing system, possibly as a step towards the development of a vision substitution device for the blind. The application of an invertible (1-to-1) image-to-sound mapping ensures the preservation of visual information. The system implementation involves a pipelined special purpose computer connected to a standard television camera. The time-multiplexed sound representations, resulting from a real-time image-to-sound conversion, represent images up to a resolution of 64 x 64 pixels with 16 gray-tones per pixel. A novel design and the use of standard components have made for a low-cost portable prototype conversion system having a power dissipation suitable for battery operation. Computerized sampling of the system output and subsequent calculation of the approximate inverse (sound-to-image) mapping provided the first convincing experimental evidence for the preservation of visual information in the sound representations of complicated images. However, the actual resolution obtainable with human perception of these sound representations remains to be evaluated.

Differentiated audio-tactile correspondences in sighted and blind individuals.

“…Several devices dedicated to assisting blind individuals (e.g. the vOICe, Meijer, 1992;Vibe, Hanneton et al, 2010) or navigation in the absence of vision (e.g. the Flybar, see have been designed by using the correspondence between direction of pitch and direction of movement (higher-higher; lower-lower) but without testing whether this correspondence, intuitive for the designers and well-documented in audio-visual contexts for sighted individuals, was also relevant for blind people.…”

ATAD: Una Ayuda Técnica para la Autonomía en el Desplazamiento

“…Atendiendo específicamente a las ayudas a la movilidad basadas en procesado de imagen y codificación en sonidos, podemos encontrar, entre otras, las siguientes: Sonic Pathfinder (Heyes, 2004), Tyflos (Bourbakis & Kavraki, 2001), Echolocation (Ifukube et al, 1991), vOICe (Meijer, 1992), FIU Project (Aguerrevere et al, 2004), 3-D Space Perceptor (Milios et al, 2003), NAVI (Sainarayanan, 2007), SVETA (Balakrishnan et al, 2006;Aguerrevere et al, 2004), AudioMan (Xu (Kawai & Tomita, 2001), Brigham Project (Lee et al, 2008), The Optophone (Capp & Picton, 2000) o The Cross-Modal ETA (Fontana et al, 2002). La idea general de todas estas ayudas técnicas es la misma: un sistema de captura de imágenes o información del entorno -en algunos casos, es multimodal, como en (Bourbakis & Kavraki, 2001) o basado en ultrasonidos, como el proyecto descrito en (Shoval, 1998) o el Pathfinder-, transmite esa información a un módulo de generación de sonidos.…”

“…El peso es otro problema importante de la mayoría de las AT comerciales, así como la dificultad de uso, es decir, cuán complejo es el dispositivo y su uso: "Los usuarios se volvían locos con el Ultracane", dijo una entrevistada. Este parámetro está relacionado con un tiempo de entrenamiento largo, como es el caso del EAV (Gonzalez-Mora et al, 2006) o el vOICe (Meijer, 1992).…”

Sonification of 3D Scenes in an Electronic Travel Aid for the Blind

“…Because of the much lower perception capacity of the human auditory (or tactile) system in comparison to visual perception, some form of image analysis or data pre-selection must be applied before the auditory code can be synthesized and presented to the blind user. One such system built in the Nederland, the vOICe, scans the image of a scene in short one-second cycles (Meijer, 1992). Image contents in the columns of pixels that move from left to right are converted into sound patterns.…”