A hardware implementation of pulse coupled neural network (PCNN) for image feature extraction
Corressponding author's email:
tapchikhgkdt@hcmute.edu.vnKeywords:
PCNN, feature vector, MSEAbstract
Couple Pulse Neural Network (PCNN) is the artificial neural network model was invented based on the visual cortex model of animals. Compared with other traditional processing methods, PCNN has some advantages such as not require training data, invariant to geometrical transformations of an image, robust against noise, highly stable structure. In this paper, the authors present results of a research on PCNN model and its applications in image feature extraction and image recognition. The proposed PCNN model is verified by the simulation results obtained from both Matlab software and FPGA implemetation. The demonstration is an image feature extraction block whose output is a feature vector of the input image. The mean
square error (MSE) between the feature vector of the input image and standard feature vector is used as the criteria to recognize, classify the image. Images are used for this study are gray level ones. Experimental results show good agreements between Matlab software implementation and hardware implementation.
Downloads: 0
References
Zhaobin Wang, Yide Ma, Feiyan Cheng, Lizhen Yang, Review of pulse-coupled neural networks, Image and Vision Computing, 2009.
T. Lindblad and J.M. Kinser, Image Processing Using Pulse-Coupled Neural Networks, Springer, 2005.
J.L. Johnson and M.L. Padgett, PCNN models and applications, IEEE Transactions on Neural Networks, 1999.
Xiaodong Gu, Feature Extraction using Unit-linking Pulse Coupled Neural Network and its Applications, Springer Science+Business Media, 10 November 2007.
D. Yamaoka, Y. Ogawa, K. Ishimura, M. Wada, Motion segmentation using pulse-coupled neural network, SICE kmual Conference in Fukui, 2003.
Y. Ma, R. Dai and L. Li, Automated image segmentation using pulse-coupled neural networks and image’s entropy, Journal of Chinese Institute of Communication, 2002.
Liang Zhou, Yu Sun, Jianguo Zheng, Automated Color Image Edge Detection Using Improved PCNN Model, WSEAS Transactions on Computers, Issue 4, Volume 7, April 2008.
Y. Ma and H. Zhang, A new image denoising algorithm combined PCNN with gray-scale morphology, Journal of Beijing University of Posts & Telecommunications, 2008.
Vega-Pineda J, Chacon-Murguia MI, Camarillo-Cisneros R, Synthesis of Pulsed-Coupled Neural Networks in FPGAs for Real-Time Image Segmentation, IEEE World Congress on Computational Intelligence Proceedings, July 16-21 2006.
Thomas Lindblad, Inherent Features of Wavelets and Pulse Coupled Neural Networks, IEEE Trans. on neuralnetworks, pp.607-614, 1999.
Waldemark Joakim, Millberg Mikael and Lindblad Thomas, Implementation of a PulsedCoupled Neural Networks in FPGA, International Journal of Neural Systems, Vol.10, No.3.pp. 171-177, June 2000.
R. Forgác, I. Mokriš, Algorithm for Pulse Coupled Neural Network Parameters Estimation, IEEE 7th International Conference on Computational Cybernetics, November 26-29, 2009.
Yide Ma and Lian Li et al., Principle of Pulse-Coupled Neural Network and Its Applications, Science Press, Beijing, China, 2006.
Hitoshi Yamada, Yuuki Ogawa, Kosei Ishimura, Mitsuo Wada, Face Detection using Pulse-Coupled Neural Network, SICE Annual Conference in Fukui, August 4-6, 2003.
Kinser.J.M, A Simplified Pulse-Coupled Neural Network, Proceedings, SPIE, Vol. 2760, No. 3, 1996
Downloads
Published
How to Cite
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.
