Automated segmentation of point data in a feature-based reverse engineering system

Abstract

This paper proposes a novel methodology for robust segmentation of scanned point data that has been implemented in the feature-based reverse engineering system (FBRES). In the proposed method, firstly triangle meshes are generated from the input point data. The normal and the area of generated meshes are checked to find boundary meshes using the angle deviation criterion and the area criterion based upon a region-growing technique. Boundary meshes of each segmented region are connected into loops. Then, the meshes closed by each boundary loop are segmented into a single distinctive region. Finally, all segmented regions are mapped into a single feature using an artificial neural network (ANN) based feature recognizer. The FBRES is currently dedicated for reconstructing prismatic features such as a block, pocket, step, slot, hole and boss, which are very common and crucial in mechanical engineering products. The effectiveness of the proposed segmentation method is validated with experimental results.

Keywords

segmentation reverse engineering feature reconstruction

References

Varady

Martin

Cox

Reverse engineering of geometric modelsâan introduction. Computer-Aided Des., 1997, 29(4), 255–268.

Raja

Lawrie

The scope of reverse engineering within engineering businesses. Engineering Development International, Official Publication of FEANI, United Kingdom, 1997.

Milroy

Bradley

Vickers

G. W.

Segmentation of a wrap-around model using an active contour. Computer-Aided Des., 1997, 29, 299–320.

Besl

P. J.

Jain

R. C.

Segmentation through variable-order surface fitting. IEEE Trans. Pattern Analysis and Mach. Intell., 1988, 10(2), 167–192.

Jun

Raja

H. V.

Park

Geometric feature recognition for reverse engineering using neural networks. Int. J. Advd Mfg Technol., 2001, 17, 462–470.

Park

Jun

Face-based reverse engineering approach to primitive analytic surfaces. In 2000 International CIRP Design Seminar, Haifa, Israel, May 2000, pp. 423–428.

Thompson

Owen

James

Feature-based reverse engineering of mechanical parts. Technical Report UUCS-95-010, University of Utah, Department of Computer Science, 6 November 1995.

Motavalli

Shamsaasef

Object-oriented modelling of a feature-based reverse engineering system. Int. J. CIM, 1996, 9(5), 354–368.

Chivate

Jablokow

Solid-model generation from measured point data. Computer-Aided Des., 1993, 25(9), 587–599.

10.

Canny

A computational approach to edge detection. IEEE Trans. Pattern Analysis and Mach. Intell., 1986, 8(6), 679–698.

11.

Dickinson

S. J.

Metaxas

Pentland

Constrained recovery of deformable models from range data. In Proceedings of International Workshop on Visual Form, Capri, Italy, 2000.

12.

Hoffman

Jain

A. K.

Segmentation and classification of range images. IEEE Trans. Pattern Analysis and Mach. Intell., 1987, 9(5), 608–620.

13.

Hoffman

Richards

Parts of recognition. Cognition, 8, 65–96.

14.

Park

Jun

Automated segmentation of scanned point data in FBRES. In 2001 International CIRP Design Seminar, Stockholm, Sweden, June 2001, pp. 353–358.

15.

Checchin

Trassoudaine

Alizon

Segmentation of range images into planar regions. In Proceedings of International Conference on Recent Advance in 3D Digital Imaging and Modeling, 1997, pp. 156–163.

16.

Bolle

Cooper

On optimally combining pieces of information, with application to estimating 3D complex-object position from range data. IEEE Trans. Pattern Analysis and Mach. Intell., 1986, 8(5), 619–638.