Future Work

We have demonstrated that the needle-map is a useful representation for object recognition, proving more stable to small changes of viewpoint than raw intensity images. This implies a significant saving in the number of model views which must be stored and matched for each object.

We have also investigated the use of the shape index, a measure designed to capture variations of surface curvature. However, in conjunction with SFS, the shape index performs significantly worse than using the needle-map directly.

There is extensive scope for further work, not least because the results presented here are derived using an extremely simple recognition technique. A more rigorous analysis is needed of how many CVs need be stored to achieve the same recognition accuracy using the needle-map and the raw image representations.