Automatic segmentation of digitized data for reverse engineering applications

Reverse engineering is the process of developing a Computer Aided Design (C AD) model and a manufacturing database for an existing part. This process i s used in CAD modeling of part prototypes, in designing molds, and in autom ated inspection of parts with complex surfaces. The work reported in this p aper is on the automatic segmentation of 3-Dimensional (3-D) digitized data captured by a laser scanner or a Coordinate Measuring Machine (CMM) for re verse engineering applications. Automatic surface segmentation of digitized data is achieved using a combination of region and edge based approaches. It is assumed that the part surface contains planar as well as curved surfa ces that are embedded in a base surface. The part surface should be visible to a single scanning probe (21/2D object). Neural network algorithms are d eveloped for surface segmentation and edge detection. A back propagation ne twork is used to segment part surfaces into surface primitives which are ho mogenous in their intrinsic differential geometric properties. The method i s based on the computation of Gaussian and mean curvatures of the surface. They are obtained by locally approximating the object surface using quadrat ic polynomials. The Gaussian and mean curvatures are used as input to the n eural network which outputs an initial region-based segmentation in the for m of a curvature sign map. An edge based segmentation is also performed usi ng the partial derivatives of depth values. Here, the output of the Laplaci an operator and the unit surface normal are computed and used as input to a Self-Organized Mapping (SOM) network. This network is used to find the edg e points on the digitized data. The combination of the region based and the edge based approaches, segment the data into primitive surface regions. Th e uniqueness of our approach is in automatic calculation of the threshold l evel for segmentation, and on the adaptability of the method to various noi se levels in the digitized data. The developed algorithms and sample result s are described in the paper.