Rapid prototyping based on image information in reverse design applications

Abstract

Rapid prototyping (RP) techniques have revolutionized traditional manufacturing methods. These techniques allow the user to fabricate a part directly from a conceptual model before investing in production tooling. However, significant time is required to complete the geometric modelling stage. This paper describes the development of an image-based rapid prototyping approach which can be used to generate geometric models in reverse design applications. The method, which uses standard two-dimensional photography, integrates the Torrance-Sparrow illumination model and the photometric stereo technique. A neural network approach is employed to decide the illumination parameters and the solution of the model. A range of examples has shown this method to be feasible and efficient to support the RP applications.