Improving appearance-based object recognition in cluttered backgrounds

Appearance-based object recognition systems are currently the most successful approach for dealing with 3D recognition of arbitrary objects in the presence of clutter and occlusion. However, no current system seems directly scalable to human performance levels in this domain. We describe a series of experiments on a previously described object recognition system that try to see, if any, which design axes of such systems hold the greatest potential for improving performance. We look at the potential effect of different design modifications, and conclude that the greatest leverage lies at the level of intermediate feature construction