×

Edge detection of noisy images based on cellular neural networks. (English) Zbl 1227.68101

Summary: This paper studies a technique employing both cellular neural networks (CNNs) and linear matrix inequality (LMI) for edge detection of noisy images. Our main work focuses on training templates of noise reduction and edge detection CNNs. Based on Lyapunov stability theorem, we derive a criterion for global asymptotical stability of a unique equilibrium of the noise reduction CNN. Then we design an approach to train edge detection templates, and this approach can detect the edge precisely and efficiently, i.e., by only one iteration. Finally, we illustrate performance of the proposed methodology from the aspect of peak signal to noise ratio (PSNR) through computer simulations. Moreover, some comparisons are also given to prove that our method outperforms classical operators in gray image edge detection.

MSC:

68T10 Pattern recognition, speech recognition
68T05 Learning and adaptive systems in artificial intelligence
93D20 Asymptotic stability in control theory
94A08 Image processing (compression, reconstruction, etc.) in information and communication theory

Software:

CNN
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Chua, L. O., CNN: a version of complexity, Int J Bifurcat Chaos, 7, 10, 2219-2425 (1997) · Zbl 0901.68138
[2] Min LQ, Zhang XJ. Robust Designs of a kind of uncoupled CNNs with Nonlinear Templates. In: Proceedings of international conference on communications, circuits and systems;2008. p. 978-981.; Min LQ, Zhang XJ. Robust Designs of a kind of uncoupled CNNs with Nonlinear Templates. In: Proceedings of international conference on communications, circuits and systems;2008. p. 978-981.
[3] Chua, L. O.; Yang, L., Cellular neural networks: theory, IEEE Trans Circ Syst, 35, 10, 1257-1272 (1988) · Zbl 0663.94022
[4] Chua, L. O.; Yang, L., Cellular neural networks: applications, IEEE Trans Circ Syst, 35, 10, 1273-1290 (1988)
[5] Zarandy, A., The art of CNN template design, Int J Circ Theory Appl, 27, 1, 5-23 (1999) · Zbl 0920.68107
[6] Harrer H, Nossek JA, Roska T, Chua LO. A current-mode DTCNN universal chip. In: Proceedings of IEEE international symposium on circuits and systems;1994. p. 135-138.; Harrer H, Nossek JA, Roska T, Chua LO. A current-mode DTCNN universal chip. In: Proceedings of IEEE international symposium on circuits and systems;1994. p. 135-138.
[7] Cruz JM, Chua LO, Roska T. A fast, complex and efficient test implementation of the CNN universal machine. In: Proceedings of 3th IEEE international workshop on cellular neural networks and their application;Rome, December 1994. p. 61-66.; Cruz JM, Chua LO, Roska T. A fast, complex and efficient test implementation of the CNN universal machine. In: Proceedings of 3th IEEE international workshop on cellular neural networks and their application;Rome, December 1994. p. 61-66.
[8] Espejo S, Dominguez-Castro R, Rodriguez-Vázquez A, Carmona R. CNNUC2 User’s guide, Centro Nacional de Microelectrónica, Seville;1995.; Espejo S, Dominguez-Castro R, Rodriguez-Vázquez A, Carmona R. CNNUC2 User’s guide, Centro Nacional de Microelectrónica, Seville;1995.
[9] Roska, T.; Chua, L. O., The CNN universal machine: an analogic array computer, IEEE Trans Circ Syst II, 40, 3, 163-173 (1993) · Zbl 0800.68251
[10] Anguita, M.; Pelayo, F. J.; Fernandez, F. J.; Prieto, A., A low-power CMOS implementation of programmable CNN’s with embedded photosensors, IEEE Trans Circ Syst I: Fundam Appl, 44, 2, 149-153 (1997)
[11] Liu, D., Cloning template design of cellular neural networks for associative memories, IEEE Trans Circ Syst I: Fundam Theory Appl, 44, 7, 646-650 (1997) · Zbl 0889.68127
[12] Fajfar, I.; Bratkovic, F.; Tuma, T.; Puhan, J., A rigorous design method for binary cellular neural networks, Int J Circ Theory Appl, 26, 4, 365-373 (1998) · Zbl 0983.94069
[13] Su, T. J.; Wei, C. P.; Huang, S. C.; Hou, C. L., Image noise cancellation using linear matrix inequality and cellular neural networks, Opt Commun, 281, 23, 5706-5712 (2008)
[14] Bastürk, A.; Günay, E., Efficient edge detection in digital images using a cellular neural networks optimized by differential evolution algorithm, Exp Syst Appl, 36, 2, 2645-2650 (2009), part 2
[15] Lin YJ, Hou CL, Su TJ. Cellular neural networks for noise cancellation of gray image based on hybrid linear matrix inequality and particle swarm optimization. In: Proceedings of the 2009 international conference on new trends in information and service science;2009. p. 613-617.; Lin YJ, Hou CL, Su TJ. Cellular neural networks for noise cancellation of gray image based on hybrid linear matrix inequality and particle swarm optimization. In: Proceedings of the 2009 international conference on new trends in information and service science;2009. p. 613-617.
[16] Fornarelli, G.; Giaquinto, A., Adaptive particle swarm optimization for CNN associative memories design, Neurocomputing, 72, 16-18, 3851-3862 (2009)
[17] He, Q. B.; Chen, F. Y., Designing cnn genes for binary images edge smoothing and noise removing, Int J Bifurcat Chaos, 16, 10, 3007-3013 (2006) · Zbl 1185.94010
[18] Chen, F. J.; Chen, F. Y.; He, G. L., Image processing via CNN genes with von neumann neighborhoods, Int J Bifurcat Chaos, 15, 12, 3999-4006 (2005) · Zbl 1093.68660
[19] Hänggi, M.; Moschytz, G. S., An exact and direct analytical method for the design of optimally robust CNN templates, IEEE Trans Circ Syst I, Fundam Theory Appl, 46, 2, 304-311 (1999)
[20] Zamparelli, M., Genetically trained cellular neural networks, Neural Netw, 10, 6, 1143-1151 (1997)
[21] Chua, L. O.; Roska, T., Cellular neural networks and visual computing: foundations and applications (2002), University Press: University Press Cambridge, United Kingdom
[22] De Souza SX, Suykens ME, Johan JAK, Vandewalle J. Automatic chip-specific CNN template optimization using adaptive simulated annealing. In: Proceedings of the 2003 European conference circuit theory and design;2003. p. 329-332.; De Souza SX, Suykens ME, Johan JAK, Vandewalle J. Automatic chip-specific CNN template optimization using adaptive simulated annealing. In: Proceedings of the 2003 European conference circuit theory and design;2003. p. 329-332.
[23] Liao, X. F.; Wong, K. W.; Wu, Z. F.; Chen, G. R., Novel robust stability criteria for interval delayed Hopfield neural networks, IEEE Trans Circ Syst-I, 48, 11, 1355-1358 (2001) · Zbl 1006.34071
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.