Shape feature information about a part is required to analyze the part for downstream issues such as manufacturability. One method of obtaining the feature information is feature recognition. This paper presents an approach called Curvature Region (CR) approach for feature recognition. The CR-approach categorizes features into two primitive shape classes: protrusions and depressions. In the first step, these primitive shape classes are recognized. In the next step, the primitive shape classes are analyzed using rules to obtain features. Primitive features are found by converting the boundary representation model to a higher level representation called Curvature Region Representation (CR-Rep).
| Number of Pages : | 6 |
| Published : | 06/01/1997 |
