Conclusions and Future Directions

Abstract

The perception of surface geometry plays a key role in 3-D object recognition. It is proposed that general-purpose recognition of 3-D objects from 2-D images can be performed without complete reliance on special purpose features by matching perceived surface descriptions with stored models of objects. In range imagery, the perceived surface descriptions directly represent scene surface geometry. In intensity imagery, geometric surface descriptions are only available from other intermediate level processes, such as shape from shading. In either case, the first step in general-purpose object recognition is the segmentation of a digital image into regions that correspond to physical scene surfaces. If the pixels of a digital surface can be correctly grouped into surface descriptions that have meaningful interpretations based-only on general knowledge of surfaces, this grouping process could provide an invaluable service to higher level recognition and model formation processes.