I. Introduction
Several research groups are designing neuroprotheses which aim at partly restoring vision for blind people. Among these systems, retinal implants are the most advanced (see [1] for a review). To date, two radically different approaches have been proposed: (1) the video images from an external camera are transformed into electrical pulses delivered wirelessly to an internal electrode array, (2) light entering the eye is converted into a pattern of electrical stimulations via micro-photodiodes integrated within the implant. In both devices, electrical stimulations elicit white/yellow spots of light called phosphenes [2]. The resulting crude vision is a set of phosphenes displayed in a restricted portion of the visual field (field of view of 15° to 20°) with little dynamic range (4 to 10 luminance levels per phosphene).