Visual substitution system for blind people based on SIFT description

The progress in fields science, information technology and communication have allowed, since the 1970s, developing new electronic aids for the blind in order to overcome the difficulties that the dog and cane do not respond. Among the systems of electronic substitution, are the sensory substitution systems that capture a low-resolution picture of the visual scene and transforming them into an another sensory modality (tactile or auditory). The recognition and localization of objects can address the need for mobility of the blind by travel assistance, aid to navigation and identify objects. In this paper, we propose a system of visual substitution that restores a central function of the visual system which is the identification of surrounding objects. Indeed, we are interested in evaluating fast and robust algorithms to recognize and locate objects in images. The perspectives of this work is to consider a substitute tool in the recognition of the environment for blind or visual impaired people, relying on a robust system for recognizing objects in a video scene and an auditory system to identify this information.