Sift approach matching constraints for real-time attention responsive system

To enable mobility-impaired individuals to access technology more efficiently, an ART (Attention Responsive Technology) System is currently being developed, which aims to use a person’s eye movements to enable the simple control of some devices in the room/office environment. One of the important parts of the system is to recognize the objects around the user in three-dimensional (3D) space. This paper addresses a solution to the matching problems for 3D object recognition using Lowe’s SIFT approach by applying appropriate rules and constraints in particular for objects with less surface contents.