Object oriented software for micro work piece recognition in microassembly

 

Toledo-Ramírez, G.K., Kussul, E. & Baidyk, T.

 

Centro de Ciencias Aplicadas y Desarrollo Tecnológico (CCADET), UNAM Circuito Exterior S/N CP 04510, Ciudad Universitaria, México D.F. 52-56228602 ext. 1135, Fax 56228626.

 

Received: September 5^th, 2005.
Accepted: March 16^th, 2006.

 

Abstract

The aim of this article is to describe object oriented software for the automatic micro work piece handling system. The general task of this system is the recognition of work pieces with neural classifier and detection of their positions. Other important functions of the system are work piece styles database administration, work piece database administration for neural classifier training and testing, neural classifier interface between database, user and work piece finder. The software is object oriented and widely commented, that makes its modification, adaptation and improvement easier. Most of the software modules can be used in other research projects. The software was tested on image database. The results of experiments prove its effectiveness in chosen task.

Keywords: Automatic Handling System, Neural Classifier, Technical Vision, Position Recognition, Microassembly, Object Oriented Software.

 

Resumen

El propósito de este artículo es describir un software orientado a objetos para el sistema automático de manejo de micro piezas. La tarea general del sistema es reconocer las distintas piezas de trabajo con redes neuronales y sus posiciones. Otras funciones importantes del sistema son el manejo de las bases de datos de estilo de piezas y de piezas para entrenamiento y prueba de la red neuronal, así como la interfaz del clasificador neuronal entre la base de datos, el usuario y el localizador de piezas. El software es orientado a objetos y ha sido ampliamente comentado, esto hace más fácil su modificación, adaptación y mejora. La mayor parte de los módulos de software pueden ser utilizados en otros proyectos de investigación. El software ha sido probado sobre una base de datos de imágenes de piezas. Los resultados de los experimentos prueban la efectividad del software en las tareas descritas.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgement

This work is supported in part by the projects PAPIIT IN1 16306-3, PAPIIT IN108606-3.

The authors gratefully acknowledge Oleksandr Makeyev for his constructive discussions and helpful comments.

 

References

[1] Ofeifer T. & Dussler G., Process observation for the assembly of hybrid microsystems, IEEE International Sysposium on Micromechatronics and Human Science, 2002, pp. 117-123.         [ Links ]

[2] Bleuler H., Clavel R., et al., Issues in precision motion control and microhandling, IEEE Procedings of Internationa Conference on Robotics & Automation, 2000, pp. 959-964.         [ Links ]

[3] Kussul E., Baidyk T., et al., Development of micromachine tool prototypes for microfactories, Journal of Micromechanical and Microengineer, Vol 12, 2002, pp. 795-813.         [ Links ]

[4] Kussul E., Baidyk T., et al., Development of Low Cost Microequipment, International Symposium on Micromechatronics and Human Science, 2002, pp. 125-134, Nagoya, Japan, October.         [ Links ]

[5] Friedrich C. & Vasile M., Development of the micromilling process for high- aspect- ratio microstructures, Journal of Microelectromechanical Systems, Vol. 5, 1996, pp. 33-38.         [ Links ]

[6] Ooyama N., Kokaji S., et al., Desktop machining microfactory, Proceedings of the 2nd International Worshop on Microfactories, 2000, pp. 14-17, Switzerland, October.         [ Links ]

[7] Baidyk T. & Kussul E., Application of neural classifier for flat image recognition in the process of microdevice assembly, Procceding of IEEE International Join Conference on Neural Networks, 2002, Vol 1, pp. 160-164, Hawaii, USA.         [ Links ]

[8] Jain R., Schunck B., et al. Machine Vision, McGraw Hill Inc. (1995).         [ Links ]

[9] Faugeras O., Three-dimensional Computer Vision, MIT Press, Cambridge, Massachusetts, 1993.         [ Links ]

[10] Ehrenmann M., Ambela D, et al., A comparison of four fast vision based object recognition methods for programming by demonstration applications, IEEE International Conference on Robotics & automation, 2000, pp. 1862-1867, San Francisco, CA., USA.         [ Links ]

[11] Steinhaus P., Prinzipielle Komponenten-Analyse versus multimediale Filterhistogramme, Master Thesis, Universitat Karlsruhe (TH), Germany, July, 1997.         [ Links ]

[12] Sun-Ho L., Hyun-Ki H., et al., Assembly part recognition using part-based superquadrics model, IEEE TENCON, 1999, pp. 479-482.         [ Links ]

[13] Bennamoun M. & Boashash B., A structural description based vision system for automatic object recognition, IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 27, Issue 6, December, 1997, pp. 893-906.         [ Links ]

[14] Detter H. & Radjenovic M., Recognition of thin, flat microelectromechanical structures for automation of the assembly process, Journal of intelligent Manufacturing, Vol. 8, No. 3, Jun, 1997, pp. 191-201.         [ Links ]

[15] Mitzias D., Mertzios B., A neural multiclassifier system for object recognition in robotic vision applications, Measurement 36, Elsevier, 2004, pp. 315-330.         [ Links ]

[16] Mardanov A., Seyfried J. et al., An automated assembly system for a microassembly station, Computer in Industry 38, Elsevier, 1999, pp. 93-102.         [ Links ]

[17] Toledo G., Kussul E., et al., Neural classifier LIRA for recognition of micro work pieces and their positions in the processes of microassembly and micromanufacturing, The Seventh All-Ukrainian International Conference on Signal/Image Processing and Pattern Recognition, 2004, pp. 17-20, Kiev, Ukraine, October.         [ Links ]

[18] Baidyk T., Kussul E., et al., Flat Image recognition in the process of microdevice assembly, Pattern Recognition Letters, Elsevier, Vol 25, 2004, pp. 107-118.         [ Links ]

[19] Rossenblatt F., Principles of Neurodynamics, Spartan books, New York, 1962.         [ Links ]

[20] Kussul E. & Baidyk T., Improved method of handwritten digit recognition tested on MNIST database, 15-th International Conference on Vision Interface, 2002, pp. 192-197, Calgary, Canada.         [ Links ]