ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Modular Cellular Neural Network Structure for Wave-Computing-Based Image Processing

  • Karami, Mojtaba (Department of Computer Engineering, Amirkabir University of Technology) ;
  • Safabakhsh, Reza (Department of Computer Engineering, Amirkabir University of Technology) ;
  • Rahmati, Mohammad (Department of Computer Engineering, Amirkabir University of Technology)
  • Received : 2012.04.21
  • Accepted : 2012.10.26
  • Published : 2013.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper introduces the modular cellular neural network (CNN), which is a new CNN structure constructed from nine one-layer modules with intercellular interactions between different modules. The new network is suitable for implementing many image processing operations. Inputting an image into the modules results in nine outputs. The topographic characteristic of the cell interactions allows the outputs to introduce new properties for image processing tasks. The stability of the system is proven and the performance is evaluated in several image processing applications. Experiment results on texture segmentation show the power of the proposed structure. The performance of the structure in a real edge detection application using the Berkeley dataset BSDS300 is also evaluated.

Keywords

References

  1. M.B. Shahram and S. Mehdi, "An Imperialist Competitive Algorithm Artificial Neural Network Method to Predict Oil Flow Rate of the Wells," Int. J. Comput. Appl., vol. 26, no. 10, July 2011, pp. 47-50.
  2. C.W. Chen, "Modeling and Control for Nonlinear Structural Systems via a NN-Based Approach," Expert Syst. Appl., vol. 36, no. 3, 2009, pp. 4765-4772. https://doi.org/10.1016/j.eswa.2008.06.062
  3. M.L. Lin and C.W. Chen, "Application of Fuzzy Models for the Monitoring of Ecologically Sensitive Ecosystems in a Dynamic Semi-arid Landscape from Satellite Imagery," Eng. Comput., vol. 27, no. 1, 2010, pp. 5-19. https://doi.org/10.1108/02644401011008504
  4. C.W. Chen, "Application of Fuzzy-Model-Based Control to Nonlinear Structural Systems with Time Delay: An LMI Method," J. Vibration Control, vol. 16, no. 11, 2010, pp. 1651- 1672. https://doi.org/10.1177/1077546309104185
  5. C.W. Chen and J. Balthazar, "Modeling and Fuzzy PDC Control and Its Application to an Oscillatory TLP Structure," Mathematical Problems Eng., vol. 2010, 2009, p. 39.
  6. C.W. Chen, K. Yeh, and K.F.R. Liu, "Adaptive Fuzzy Sliding Mode Control for Seismically Excited Bridges with Lead Rubber Bearing Isolation," Int. J. Uncertainty, Fuzziness Knowl. Syst., vol. 17, no. 5, 2009, p. 705. https://doi.org/10.1142/S0218488509006224
  7. C.W. Chen and P.C. Chen, "GA-Based Adaptive Neural Network Controllers for Nonlinear Systems," Int. J. Innov. Comput. Inf. Control, vol. 6, 2010, pp. 1793-1803.
  8. C.P. Tseng, C.W. Chen, and K.F.R. Liu, "Risk Control Allocation Model for Pressure Vessels and Piping Project," J. Vibration Control, vol. 18, no. 3, 2012, pp. 385-394. https://doi.org/10.1177/1077546311403182
  9. K. Yeh et al., "Neural-Network Fuzzy Control for Chaotic Tuned Mass Damper Systems with Time Delays," J. Vibration Control, vol. 18, no. 6, 2011, pp. 785-795.
  10. T. Roska, "Computational and Computer Complexity of Analogic Cellular Wave Computers," J. Circuits Syst. Comput., vol. 12, no. 4, 2003, pp. 539-556. https://doi.org/10.1142/S0218126603001021
  11. L.O. Chua and L. Yang, "Cellular Neural Networks: Theory," IEEE Trans. Circuits Syst., vol. 35, no. 10, 1988, pp. 1257-1272. https://doi.org/10.1109/31.7600
  12. L.O. Chua and L. Yang, "Cellular Neural Networks: Applications," IEEE Trans. Circuits Syst., vol. 35, no. 10, 1988, pp. 1273-1290. https://doi.org/10.1109/31.7601
  13. T. Roska and L.O. Chua, "The CNN Universal Machine: An Analogic Array Computer," IEEE Trans. Circuits Syst. II, Analog Digit. Signal Process., vol. 40, no. 3, 1993, pp. 163-173. https://doi.org/10.1109/82.222815
  14. L.O. Chua and T. Roska, "The CNN Paradigm," IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol. 40, no. 3, 1993, pp. 147-156. https://doi.org/10.1109/81.222795
  15. L.O. Chua and T. Roska, Cellular Neural Networks and Visual Computing: Foundation and Applications, Cambridge, UK: Cambridge University Press, 2002.
  16. T. Roska, "Circuits, Computers, and Beyond Boolean Logic," Int. J. Circuit Theory Appl., vol. 35, no. 5-6, 2007, pp. 485-496. https://doi.org/10.1002/cta.437
  17. T. Roska, "Analogic CNN Computing: Architectural, Implementation, and Algorithmic Advances - A Review," Proc. IEEE Int. Workshop Cellular Neural Netw. Appl., 1998, pp. 3-10.
  18. M. Pavone et al., "Climbing Obstacle in Bio-Robots via CNN and Adaptive Attitude Control," Int. J. Circuit Theory Appl., vol. 34, no. 1, 2006, pp. 109-125. https://doi.org/10.1002/cta.345
  19. R. Tetzlaff, C. Niederhöfer, and P. Fischer, "Automated Detection of a Preseizure State: Non-linear EEG Analysis in Epilepsy by Cellular Nonlinear Networks and Volterra Systems," Int. J. Circuit Theory Appl., vol. 34, no. 1, 2006, pp. 89-108. https://doi.org/10.1002/cta.344
  20. G. Cserey, A. Falus, and T. Roska, "Immune Response Inspired Spatial-Temporal Target Detection Algorithms with CNN-UM," Int. J. Circuit Theory Appl., vol. 34, no. 1, 2006, pp. 21-47. https://doi.org/10.1002/cta.341
  21. I. Szatmári, "Object Comparison Using PDE-Based Wave Metric on Cellular Neural Networks," Int. J. Circuit Theory Appl., vol. 34, no. 4, 2006, pp. 359-382. https://doi.org/10.1002/cta.361
  22. S. Xavier-de-Souza, J.A. Suykens, and J. Vandewalle, "Learning of Spatiotemporal Behaviour in Cellular Neural Networks," Int. J. Circuit Theory Appl., vol. 34, no. 1, 2006, pp. 127-140. https://doi.org/10.1002/cta.346
  23. Z. Fodróczi and A. Radványi, "Computational Auditory Scene Analysis in Cellular Wave Computing Framework," Int. J. Circuit Theory Appl., vol. 34, no. 4, 2006,pp. 489-515. https://doi.org/10.1002/cta.362
  24. D. Bálya et al., "A CNN Framework for Modeling Parallel Processing in a Mammalian Retina," Int. J. Circuit Theory Appl., vol. 30, no. 2-3, 2002, pp. 363-393. https://doi.org/10.1002/cta.204
  25. D. Bálya et al., "Implementing the Multilayer Retinal Model on the Complex-Cell CNN-UM Chip Prototype," Int. J. Bifurc. Chaos, vol. 14, no. 2, 2004, pp. 427-451. https://doi.org/10.1142/S0218127404009302
  26. V.I. Krinsky, V.N. Biktashev, and I.R. Efimov, "Autowave Principles for Parallel Image Processing," Physica D: Nonlinear Phenomena, vol. 49, no. 1-2, 1991, pp. 247-253. https://doi.org/10.1016/0167-2789(91)90213-S
  27. V. Perez-Munuzuri, V. Perez-Villar, and L.O. Chua, "Autowaves for Image Processing on a Two-Dimensional CNN Array of Excitable Nonlinear Circuits: Flat and Wrinkled Labyrinths," IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol. 40, no. 3, 1993, pp. 174-181. https://doi.org/10.1109/81.222798
  28. T. Roska et al., "Simulating Nonlinear Waves and Partial Differential Equations via CNN - Part I: Basic Techniques," IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol. 42, no. 10, 1995, pp. 807-815. https://doi.org/10.1109/81.473590
  29. T. Kozek et al., "Simulating Nonlinear Waves and Partial Differential Equations via CNN - Part II: Typical Examples," IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol. 42, no. 10, 1995, pp. 816-820. https://doi.org/10.1109/81.473591
  30. C. Rekeczky, "CNN Architectures for Constrained Diffusion Based Locally Adaptive Image Processing," Int. J. Circuit Theory Appl., vol. 30, no. 2-3, 2002, pp. 313-348. https://doi.org/10.1002/cta.202
  31. C. Rekeczky and L.O. Chua, "Computing with Front Propagation: Active Contour and Skeleton Models in Continuous-Time CNN," J. VLSI Signal Process., vol. 23, no. 2, 1999, pp. 373-402. https://doi.org/10.1023/A:1008153320440
  32. S. Majorana and L.O. Chua, "A Unified Framework for Multilayer High Order CNN," Int. J. Circuit Theory Appl., vol. 26, no. 6, 1999, pp. 567-592.
  33. Z. Yang, Y. Nishio, and A. Ushida, "Characteristic of Mutually Coupled Two-Layer CNN and Its Stability," J. Circuits Syst. Comput., vol. 12, no. 4, 2003, pp. 473-490. https://doi.org/10.1142/S0218126603000982
  34. B.E. Shi, "An Eight Layer Cellular Neural Network for Spatio- Temporal Image Filtering," Int. J. Circuit Theory Appl., vol. 34, no. 1, 2006, pp. 141-164. https://doi.org/10.1002/cta.347
  35. M.L. Lin and C.W. Chen, "Stability Analysis of Community and Ecosystem Hierarchies Using the Lyapunov Method," J. Vibration Control, vol. 17, no. 13, 2011, pp. 1930-1937. https://doi.org/10.1177/1077546310385737
  36. K. Yeh, C.W. Chen, and C. Cattani, "Stability Analysis of Interconnected Fuzzy Systems Using the Fuzzy Lyapunov Method," Mathematical Problems Eng., vol. 2010, 2009, pp. 34- 43.
  37. K. Yeh, C.Y. Chen, and C.W. Chen, "Robustness Design of Time-Delay Fuzzy Systems Using Fuzzy Lyapunov Method," Appl. Mathematics Comput., vol. 205, no. 2, 2008, pp. 568-577. https://doi.org/10.1016/j.amc.2008.05.104
  38. C.W. Chen et al., "Stability Analysis of an Oceanic Structure Using the Lyapunov Method," Eng. Comput.: Int. J. Computer Aided Eng., vol. 27, no. 2, 2010, pp. 186-204.
  39. P.C. Chen, C.W. Chen, and W.L. Chiang, "Linear Matrix Inequality Conditions of Nonlinear Systems by Genetic Algorithm-Based $H_{\infty}$ Adaptive Fuzzy Sliding Mode Controller," J. Vibration Control, vol. 17, no. 2, 2011, pp. 163-173. https://doi.org/10.1177/1077546309352826
  40. T. Roska, "Cellular Wave Computers for Brain-like Spatial Temporal Sensory Computing," IEEE Circuits Syst. Mag., vol. 5, no. 2, 2005, pp. 5-19.
  41. C. Rekeczky et al., "Analogic Cellular PDE Machines," Proc. IJCNN, 2002, pp. 2033-2038.
  42. C. Rekeczky and T. Roska, "Calculating Local and Global PDEs by Analogic Diffusion and Wave Algorithms," Proc. European Conf. Circuit Theory Des., vol. 2, 2001, pp. 17-20.
  43. L. Kék, K. Karacs, and T. Roska, Cellular Wave Computing Library: Templates, Algorithms, and Programs, V. 2.1, Budapest, Hungary: MTA-SZTAKI, 2007.
  44. K.R. Crounse and L.O. Chua, "Methods for Image Processing and Pattern Formation in Cellular Neural Networks: A Tutorial," IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol. 42, no. 10, 1995, pp. 583-601. https://doi.org/10.1109/81.473566
  45. T.M. Apostol, Calculus, Volume 2, Multi-Variable Calculus and Linear Algebra with Applications, New York: Wiley, 1969.
  46. C.D. Meyer, Matrix Analysis and Applied Linear Algebra, Philadelphia, PA: Society for Industrial Mathematics, 2000.
  47. W.H. Steeb and T.K. Shi, Matrix Calculus and Kronecker Product with Applications and C++ Programs, Hackensack, NJ: World Scientific Pub Co Inc., 1997.
  48. G.E. Pazienza, E. Gomez-Ramirez, and X. Vilasis-Cardona, "Genetic Programming for the CNN-UM," 10th Int. Workshop CNNA, 2006, pp. 1-6.
  49. T. Szirányi and M. Csapodi, "Texture Classification and Segmentation by Cellular Neural Networks Using Genetic Learning," Comput. Vision Image Understanding, vol. 71, no. 3, 1998, pp. 255-270. https://doi.org/10.1006/cviu.1997.0646
  50. T. Roska, Software Library for Cellular Wave Computing Engines V. 3.1, Budapest, Hungary: MTA-SZTAKI and Pazmany University, 2010.
  51. J.A. Hernandez, F.G. Castaneda, and J.A. Cadenas, "A Method for Edge Detection in Gray Level Images, Based on Cellular Neural Networks," 52nd IEEE Int. MWSCAS, 2009, pp. 730-733.
  52. D. Martin et al., "A Database of Human Segmented Natural Images and Its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics," Proc. 8th IEEE Int. Conf. Comput. Vision, vol. 2, 2001, pp. 416-423.
  53. P. Arbelaez et al., "Contour Detection and Hierarchical Image Segmentation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 5, 2010, pp. 898-916.
  54. D. Martin, C. Fowlkes, and J. Malik, "Learning to Detect Natural Image Boundaries Using Brightness and Texture," Neural Inf. Process. Syst., 2002, pp. 1255-1262.
  55. D.R. Martin, C. Fowlkes, and J. Malik, "Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues," IEEE Trans. Pattern Anal., vol. 26, no. 5, 2004, pp. 530-549. https://doi.org/10.1109/TPAMI.2004.1273918
  56. C. Rekeczky, MATCNN - Analogic CNN Simulation Toolbox for Matlab, Version 1.0, DNS-11-1997, technical report, Analogical and Neural Computing Laboratory, Computer and Automation Institute of the Hungarian Academy of Sciences, Budapest, Hungary, Sept. 1997.

Cited by

  1. Systematic Research on the Application of Steel Slag Resources under the Background of Big Data vol.2018, pp.None, 2018, https://doi.org/10.1155/2018/6703908
  2. A review of modularization techniques in artificial neural networks vol.52, pp.1, 2013, https://doi.org/10.1007/s10462-019-09706-7