a neural network approach to CSG-Based 3-D object recognition
tsu-Wang Chen and Wei-Chung Lin
object representation and recognition, constructive solid geometry (CSG), range image, precedence graph, neural networks, and mean field annealing
In this correspondence, we describe the recognition subsystem of a computer vision system based on Constructive Solid Geometry (CSG) representaticn scheme. Instead of using the conventional CSG trees to represent objects, the proposed system uses an equivalent representation schemeprecedence graphefor object representation. Each node in the graph represents a primitive volume and each arc between two nodes represents the relation between them. Object recognition is achieved by matching the scene precedence graph to the model precedence graph. A constraint satisfaction network is proposed to implement the matching process. The energy function associated with the network is used to enforce the matching constraints including match validity, primitive
similarity, precedence graph preservation, and geometric structure preservation. The energy level is at its minimum only when the optimal match is reached. Experimental results on several range images are presented to demonstrate the proposed approach.
IEEE transactions on pattern analysis and machine intelligence