Recognizing features from orthographic images using neural networks: a framework for CADCAM and AVI integration

In order to satisfy the current market demands for shorter lead-time and high quality products manufacturing enterprises have to integrate their design, production and quality assurance functions. In a computerized environment these functions are manifested in CAD, CAM and AVI respectively. In the recent past, much success has been achieved in integrating CAD and CAM. It is widely accepted that feature recognition systems, both 2D and 3D, have been one of the main contributors to CADCAM integration. However the existing feature recognition systems could not link CADCAM and AVI and hence could not close the manufacturing loop that ensures the production of designer intended features. This is mainly because the input formats of existing feature recognition systems and AVI systems have been different in format and structure. The system described in this paper attempts to redress this deficit at least partially by using a monochrome bitmap as a generic input, to which both CAD models and vision images could be converted. Hence the input to the system takes a form of third angle orthographic views, however, without hidden lines in order to facilitate dealing with vision images. This, in turn, augments difficulty faced in recognizing features. To overcome this difficulty, the help of evolutionary computing and artificial intelligence is sought in this system. This paper outlines the basis of a 2D feature recognition system that uses artificial neural networks along with a chain code method for eliciting feature information from monochrome bitmap of either vision images or CAD inputs hence providing a generic framework to integrate CADCAM and AVI. With further improvement to deal with geometry of the features, annotations and symbols this system could also help to salvage the massive store of engineering knowledge that exists in 2D form.

[1]  Ferruh Öztürk,et al.  Hybrid neural network and genetic algorithm based machining feature recognition , 2004, J. Intell. Manuf..

[2]  Anil K. Jain,et al.  Segmentation and Classification of Range Images , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Leila De Floriani.  Feature Extraction from Boundary Models of Three-Dimensional Objects , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  M. Eden,et al.  On the performance of a contour coding algorithm in the context of image coding part I: Contour segment coding , 1985 .

[5]  Toru Kaneko,et al.  Encoding of Arbitrary Curves Based on the Chain Code Representation , 1985, IEEE Trans. Commun..

[6]  P. K. Venuvinod,et al.  Automated extraction of dimensional inspection features from part computer-aided design models , 2005 .

[7]  Sheik Meeran,et al.  A generic approach to recognising isolated, nested and interacting features from 2D drawings , 1999, Comput. Aided Des..

[8]  Michael J. Pratt,et al.  Automated feature recognition from 2D drawings , 1993, Comput. Aided Des..

[9]  Y. H. Chen,et al.  A neural network system feature recognition for two-dimensional , 1998, Int. J. Comput. Integr. Manuf..

[10]  Michael J. Pratt.  Automated Feature Recognition and its Role in Product Modelling , 1992, Geometric Modelling.

[11]  S. Fioravanti,et al.  Shape and location coding for contour images , 1995 .

[12]  Azriel Rosenfeld,et al.  The Chain Pyramid: Hierarchical Contour Processing , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Venkat Devarajan,et al.  Automatic identification of non-intersecting machining features from 2D CAD input , 1998, Comput. Aided Des..

[14]  Sheik Meeran,et al.  Feature patterns in recognizing non-interacting and interacting primitive, circular and slanting features using a neural network , 1999 .

[15]  N. N. Z. Gindy,et al.  A hierarchical structure for form features , 1989 .

[16]  Saeid Motavalli,et al.  A system for reverse engineering parts using orthographic of prismatic images , 1998, Int. J. Comput. Integr. Manuf..

[17]  David H. Douglas.  EXPERIMENTS TO LOCATE RIDGES AND CHANNELS TO CREATE A NEW TYPE OF DIGITAL ELEVATION MODEL , 1987 .

[18]  William C. Regli,et al.  Geometric algorithms for recognition of features from solid models , 1996 .

[19]  Andrew Y. C. Nee,et al.  A hybrid method for recognizing interacting machining features , 2003 .

[20]  Srichand Hinduja,et al.  Modelling turned components with non-axisymmetric features , 1997, Comput. Aided Des..

[21]  Orit Baruch,et al.  Segmentation of two-dimensional boundaries using the chain code , 1988, Pattern Recognit..

[22]  Thomas J. Peters.  Encoding mechanical design features for recognition via neural nets , 1992 .

[23]  Herbert Freeman,et al.  On the Encoding of Arbitrary Geometric Configurations , 1961, IRE Trans. Electron. Comput..

[24]  Jami J. Shah.  Assessment of features technology , 1991, Comput. Aided Des..

[25]  Hm Lee,et al.  A neural network system for two-dimensional feature recognition , 1998 .

[26]  Cihan H. Dagli,et al.  Neuro-computing and concurrent engineering , 1993 .

[27]  C. L. Li,et al.  Feature recognition by template matching , 2000, Comput. Graph..

[28]  R. Lee,et al.  Two-Dimensional Critical Point Configuration Graphs , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  T. C. Chang,et al.  Graph-based heuristics for recognition of machined features from a 3D solid model , 1988 .

[30]  Ajay Joneja,et al.  Recognizing generalized pockets for optimizing machining time in process planningPart 1 , 2001 .

[31]  Sheik Meeran,et al.  Recognition and interpretation of interacting and non-interacting features using spatial decomposition and Hamiltonian path search , 1996 .

[32]  Xun Xu,et al.  Determination of finishing features in 2½ D components , 1997 .

[33]  Hiroshi Sakurai,et al.  Definition and Recognition of Volume Features for Process Planning , 1994 .

[34]  David H. Douglas,et al.  Detection of Surface-Specific Points by Local Parallel Processing of Discrete Terrain Elevation Data , 1975 .