Recognition system object classes by artificial vision to improve communication skills in people with language disorders

摘要

The system aims at implementing recognition algorithms classes of objects in images to improve communication skills in people with language disorders. This requires a system image capture (1), in charge of obtaining the image to be processed by a module that implements a system for locating classes of objects in images (2), which is based on artificial vision techniques used . This module (2) provide a visual output (3) in which the recognized classes of objects in the image are boxed. The system will interact with the user (4), offering localized information object or question him on it so that it is he who enter the information on the recognized class. In this second mode, the system will inform the user if the exercise was completed successfully.