Cellular neural network-based object recognition with deformable grids

• Autorzy: Korbel P. , Slot K.
• Konferencja: International Conference on Computer Vision and Graphics ICCVG 2006 (25-27.09.2006 ; Warsaw, Poland)
• Języki publikacji: EN

Abstrakty

EN

The following paper presents an idea for a parallel implementation of the deformable grid paradigm within the framework of Cellular Neural Networks. Parallel processing may alleviate the problem of high complexity of deformable template matching and significantly speed up object recognition tasks. The paper presents details of a CNN-based implementation of the basic element of the deformable grid-based image processing, which is image-grid matching. Estimated execution speed of the CNN-based method and recognition rates achieved in the experiments make the method an attractive framework for applications such as high-speed coarse object classification.

Słowa kluczowe

EN

object recognition; image processing; cellular neural networks

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2006
• Tom: Vol. 15, No. 3/4
• Strony: 461--469
• Opis fizyczny: Bibliogr. 12 poz., il., tab., wykr.

Twórcy

autor

Korbel P.

autor

Slot K.

• Technical University od Lodz, Intitute of Electronics, Wolczanska 211/215, 90-924 Lodz, Poland,

Bibliografia

• [1] Chua L. O., Yang L.: Cellular neural networks: Theory. IEEE Transactions on Circuits and Systems, vol. 32, 1257-1272, 1988.
• [2] Roska T., Chua L. O.: The CNN Universal Machine: An Analogic Array Computer. IEEE Transactions on Circuits and Systems-II, vol. 40, 163-173, 1993.
• [3] Harrer H., Venetianer P. L., Nossek J. A., Roska T., Chua L. O.: Some Examples of Preprocessing Analog Images with Discrete-Time Cellular Neural Networks, Proceedings of the International Workshop on Cellular Neural Networks and their Applications (CNNA-94), pp. 201-206, Rome, 1994.
• [4] Venetianer P. L., Werblin F., Roska T., Chua L. O.: Analogic CNN algorithms for some image compression and restoration tasks, IEEE Transactions on Circuits and Systems, Vol. 42, No.5, 1995, 1995.
• [5] Jain A. K., Zhong Y., Lakshmanan S.: Object matching using deformable templates. IEEE Transactions on PAMI, Vol. 18, No. 3, 267-278, 1996.
• [6] Rekeczky C., Chua L. O.: Computing with front propagation: active contour and skeleton models in continuous-time CNN. Journal of VLSI Signal Processing Systems, Vol. 23, No. 2/3, 373-402, 1999.
• [7] Szczypinski P. M., Materka A.: Object tracking and recognition using deformable grid with geometrical templates. Proc. of Int. Conference on Signals and Electronic Systems ICSES 2000, Poland, 169-174, 2000.
• [8] Linan G., Dominguez-Castro R., Espejo S., Rodriguez-Vazquez A.: ACE16K: an Advanced Focal-Plane Analog Programmable Processor. Proceedings of ESSCIRC'2001, Austria, 201-204, 2001.
• [9] Linan G., Espejo S., Dominguez-Castro R., Rodriguez-Vazquez A.: ACE4K: An analog I/O visual microprocessor chip with 7-bit analog accuracy. International Journal of Circuit Theory and Applications, Vol. 30, 89-116, 2002.
• [10] Slot K., Korbel P.: Deformable grid paradigm implementation in cellular neural networks. Proceedings of CNN A 2004, Budapest, Hungary, 2004.
• [11] Zarandy A., Rekeczky C.: Bi-i: a standalone ultra high speer cellular vision system, IEEE Circuits and Systems Magazine, Second Quarter, 2005.
• [12] Korbel P., Slot K.: Modeling of elastic inter-node bounds in cellular neural network-based implementation of the deformable grid paradigm. Proceedings of CNN A 2006, Istanbul, Turkey, 2006.