Abstract
This work presents a cellular neural network (CNN) learning tool based on the Center of Mass Algorithm (CMA), which provides a friendly graphical user interface. As original contributions of this work, the learning tool here developed for CNN features a few adaptations in CMA to improve the training process for grayscale image filtering, such as decreasing learning rates and training with multiple image sets, and comprises many graphical user interface facilities for CNN designers. The training capability of the developed tool is validated through several filter applications, among which lowpass and highpass filters with finite or infinite impulse responses. A comparative analysis is performed between the theoretical responses of the filters and the results obtained from the simulation of a CMOS analog CNN configured by the parameters determined through the learning tool. The training process was very fast for the lowpass filters and acceptable RMS pixel errors have been obtained for all examples, confirming the reliability of the learning tool.
Similar content being viewed by others
References
A.A. Abdullah, B.S. Chize, Z. Zakaria, Design of cellular neural network (CNN) simulator based on Matlab for brain tumor detection. J. Med. Imag. Health Inform. 2(3), 1–11 (2012). https://doi.org/10.1166/jmihi.2012.1095
F. S. de Andrade, Y. O. da G. Souza, E. P. Santana and A. I. A. Cunha, Image filtering in a CMOS analog CNN, In: Proceedings of the 2015 IEEE 6th Latin American Symposium on Circuits & Systems. LASCAS, (2015), pp. 1–4. https://doi.org/10.1109/LASCAS.2015.7250426
F. S. Andrade, Filtragem de Imagens em Escala de Cinza por Meio de Rede Neuronal Celular Analógica em Tecnologia CMOS, M.S. thesis, Dept. of Electrical and Comput. Engineering, Univ. Federal da Bahia (UFBA), Salvador, BA, 2015.
F. S. de Andrade, E. P. Santana, A. I. A. Cunha, E. F. de Simas Filho, G. C. Gonçalves and A. J. S. de Sousa, Learning for Image Processing: Center of Mass versus Genetic Algorithms,” In: Proceedings of the 2019 IEEE 10th Latin American Symposium on Circuits & Systems. LASCAS, (2019), pp. 41–44. https://doi.org/10.1109/LASCAS.2019.8667559
A. Azamimi Abdullah, S. C. Ling and W. K. W. Ahmad, Design of an automated breast cancer masses detection in mammogram using cellular neural network (CNN) algorithm. Adv. Sci. Lett. 20(1), 254–258 (2014). https://doi.org/10.1166/asl.2014.5307
A. Baştürk, E. Günay, Efficient edge detection in digital images using a cellular neural network optimized by differential evolution algorithm. Expert Syst. Appl. 36(2), 2645–2650 (2009). https://doi.org/10.1016/j.eswa.2008.01.082
R. Carmona, F. Giménez-Garrido, R. Dominguez-Castro, S. Espejo, A. Rodríguez-Vázquez, CMOS realization of a 2-layer CNN universal machine chip. Int. J. Neural Syst. 13(6), 435–442 (2003). https://doi.org/10.1142/S0129065703001716
R. Carmona-Galán, F. Giménez-Garrido, R. Dominguez-Castro, S. Espejo, T. Roska, C. Rekeczky, I. Petrás, A. Rodríguez-Vázquez, A bio-inspired two-layer mixed-signal flexible programmable chip for early vision. IEEE Trans. Neural Networks 14(5), 1313–1333 (2003). https://doi.org/10.1109/TNN.2003.816377
L.O. Chua, L. Yang, Cellular neural networks: theory. IEEE Trans. Circuits Syst. 35(10), 1257–1272 (1988). https://doi.org/10.1109/31.7600
L.O. Chua, T. Roska, Cellular neural networks and visual computing: foundations and applications (Cambridge University Press, Cambridge, 2002)
S. Espejo, R. Carmona, R. Domínguez-Castro and A. Rodríguez-Vázquez, A VLSI-oriented continuous-time CNN model. Int. J. Circuit Theory Appl. 24(3), 341–356 (1996). https://doi.org/10.1002/(SICI)1097-007X(199605/06)24:3<341::AID-CTA920>3.0.CO;2-L
R.C. Gonzalez, R.E. Woods, S.L. Eddins, Digital image processing Using MATLAB (Pearson Prentice Hall, 2003)
C. Guzelis and S. Karamahmut, Recurrent perceptron learning algorithm for completely stable cellular neural networks, In: Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications. CNNA-94, (1994), pp. 177–182. https://doi.org/10.1109/CNNA.1994.381688.
S. Kim, C. Song, J. Jang, J. Paik, Edge-aware image filtering using a structure-guided CNN. IET Image Proc. 14(3), 472–479 (2020). https://doi.org/10.1049/iet-ipr.2018.6691
T. Kozek, T. Roska and L. O. Chua, Genetic algorithm for CNN template learning. IEEE Trans. Circuits Syst. I Fund. Theory Appl. 40(6), 392–402 (1993). https://doi.org/10.1109/81.238343.
J. Lai and P. C. Wu 2004 Architectural design and analysis of learnable self-feedback ratio-memory cellular nonlinear network (SRMCNN) for nanoelectronic systems. IEEE Trans Very Large Scale Integration (VLSI) Syst. 12(11), 1182–1191 https://doi.org/10.1109/TVLSI.2004.836309
B. Mirzai, Z. Cheng and G. S. Moschytz, Learning algorithms for cellular neural networks, In: Proceedings of the 1998 IEEE International Symposium on Circuits and Systems. ISCAS’98, vol. 3 (1998), pp. 159–162. https://doi.org/10.1109/ISCAS.1998.703935
A. Rodríguez-Vázquez, S. Espejo, R. Domínguez-Castro, J. Huertas and E. Sanchez-Sinencio, Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networks. IEEE Trans. Circuits Syst. II Analog Digital Signal Process., 40(3), 132–146 (1993). https://doi.org/10.1109/82.222812
E. Saatci and V. Tavsanoglu, Fingerprint image enhancement using CNN Gabor-type filters, In: Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications, (2002), pp. 377–382. https://doi.org/10.1109/CNNA.2002.1035073
E. Santana, R. C. Freire and A. I. Cunha, (2012) A compact low-power CMOS analog FSR model-based CNN. J. Integr. Circuits Syst. 7(1) 72–80. https://doi.org/10.29292/jics.v7i1.357
M. Tanaka, H. Aomori, K. Oshima, M. Hasler and Y. Nishio, Leaning theory of cellular neural networks based on covariance structural analysis, In: Proceedings of the 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications. CNNA 2010, (2010), pp. 1–4. https://doi.org/10.1109/CNNA.2010.5430326.
Acknowledgements
Authors would like to acknowledge Conselho Nacional de Desenvolvimento Científico e Tecnológico—CNPq, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—CAPES and Fundação de Amparo à Pesquisa do Estado da Bahia—FAPESB for the financial support.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
de Andrade, F.S., Souza, Y.O.d., Santana, E.P. et al. A Graphical Interface Learning Tool for Image Processing Through Analog CNN. Circuits Syst Signal Process 41, 4952–4976 (2022). https://doi.org/10.1007/s00034-022-02013-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-022-02013-7