Object recognition in image sequences with cellular neural networks

Neurocomputing

Volumn 31, Issue 1-4, 2000, Pages 125-141

  Milanova, Mariofanna ^a   Büker, Ulrich ^b  

^a INEB INSTITUTO DE ENGENHARIA BIOMÉDICA   (Portugal)

^b UNIVERSITY OF PADERBORN   (Germany)

Author keywords

Associative memory; Cellular neural networks; Image sequences; Object recognition; Optical flow

Indexed keywords

ASSOCIATIVE STORAGE; COMPUTATIONAL METHODS; IMAGE ANALYSIS; OBJECT RECOGNITION; OPTICAL FLOWS; PATTERN RECOGNITION SYSTEMS; THREE DIMENSIONAL COMPUTER GRAPHICS; TIME SERIES ANALYSIS; VECTORS;

IMAGE SEQUENCES;

CELLULAR NEURAL NETWORKS;

ALGORITHM; ARTIFICIAL NEURAL NETWORK; ASSOCIATIVE MEMORY; COMPUTER SYSTEM; IMAGE ANALYSIS; MATHEMATICAL COMPUTING; PATTERN RECOGNITION; PRIORITY JOURNAL; REVIEW;

EID: 0343852159     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(99)00177-0     Document Type: Article

References (27)

1. Bradski G., Grossberg S. Fast-learning VIEWNET architectures for recognizing three-dimensional objects from multiple two-dimensional views. Neural Networks. 8(7/8):1995;1053-1080.
2. U. Büker, G. Hartmann, Knowledge based view control of a neural 3D object recognition system, in: Proceedings of the 13th International Conference on Pattern Recognition, ICPR'96, Wien, Vol.IV, IEEE Computer Soc. Press, Los Alamitos, 1996, pp. 24-29.
3. U. Büker, Hybrid object models: combining symbolic and subsymbolic object recognition strategies. in: Proceedings of the 4th International Conference on Information Systems, Analysis, and Synthesis, Vol.I, IIIS, Orlando, 1998, pp. 444-451.
4. Bülthoff H., Little J., Poggio T. A parallel algorithm for real-time computation of optical flow. Nature. 337:1989;549-553.
5. H. Bülthoff, S. Edelman, M. Tarr, How are three-dimensional objects represented in the brain? Technical report, A.I.Memo N1479, Massachusetts Institute of Technology, A.I. Lab, 1994.
6. Chua L.O., Yang L. Cellular neural networks: theory. IEEE Trans. Circuits Systems. 35:1988;1257-1272.
7. Chua L.O., Roska T. The CNN Paradigm. IEEE Trans. Circuits Systems (Part I) CAS-40. 3:1993;559-577.
8. Fu L.M. Analysis of the dimensionality of neural networks for pattern recognition. Pattern Recognition. 23:1990;1131-1140.
9. Grassi G. A new approach to design cellular neural networks for associative memories. IEEE Trans. Circuits Systems - I Fundam. Theory Appl. 44(9):1997;362-366.
10. G. Hartmann, S. Drüe, J. Dunker, K.O. Kräuter, B. Mertsching, E. Seidenberg, The SENROB Vision-System and its Philosophy, in: Proceedings of the 12th International Conference on Pattern Recognition ICPR'94, Jerusalem, Vol.II, IEEE Computer Soci. Press, Los Alamitos, 1994, pp. 573-576.
11. G. Hartmann, U. Büker, S. Drüe, A hybrid neuro-artificial intelligence architecture, in: B. Jähne et al. (Eds.), Handbook on Computer Vision and Applications, Vol. III, Academic Press, San Diego, 1999, pp. 153-196.
12. M. Hebert et al. (Eds.), Object Recognition in Computer Vision, Springer, New York, 1995.
13. Kikuchi M., Fukushima K. Neural network model of the visual system: binding: form and motion. Neural Networks. 9(8):1996;1417-1427.
14. Kosslyn S.M. Image and Brain. 1995;MIT Press, Cambridge.
15. Lin W.G., Wang S.S. A new neural model for invariant pattern recognition. Neural Networks. 9(5):1996;899-913.
16. J. Little, J. Boyd, Describing motion for recognition, IEEE Symp. Comput. Vision (1995) 235-240.
17. J. Little, J. Boyd, Recognizing people by their gait: the shape of motion, On-line document, http://www-vision.ucsd.edu/, 1997.
18. Liu D., Michel A. Sparsely interconnected neural networks for associative memories with applications to cellular neural networks. IEEE Trans. Circuits Systems - II Analog Digital Signal Process. 41(4):1994;295-307.
19. Liu D. Cloning template design of cellular neural networks for associative memories. IEEE Trans. Circuits Systems - I Fundam. Theory Appl. 44(7):1997;646-650.
20. Liu D., Lu Z. A new synthesis approach for feedback neural networks based on the perceptron training algorithm. IEEE Trans. Neural Networks. 8(6):1997;1468-1482.
21. Michel A., Jie Si, Yen G. Analysis and Synthesis of a Class of Discrete-Time Neural Networks Described on Hypercubes. IEEE Trans. Neural Networks. Vol. 2(1):1991;32-46.
22. A. Pandya, R. Macy, Pattern Recognition with Neural Networks in C++, CRC Press, Florida, 1996.
23. Rekecsky C., Roska T., Ushida A. CNN-based difference-controlled adaptive non-linear image filters. Internat. J. of Circuit Theory Appl. Vol. 26(4):1998;374-423.
24. T. Roska, J. Vandewalle, Cellular Neural Networks, John Wiley & Sons, New York, 1993.
25. Szolgay P., Szatmari I., Laszlo K. A Fast Fixed Point Learning Method to Implement Associative Memory on CNN's. IEEE Trans. Circuits Systems-I: Fundamental Theory and Applications. Vol. 44(4):1997;362-366.
26. Treisman A. A feature-integration theory of attention. Cognitive Psychology. 12:1980;97-136.
27. S. Tn, J. Hao, J. Vanderwalle, Cellular neural networks as a model of associative memories, Proceedings of the CNNA-90, Budapest, IEEE, New York, 1990, 26-35.