Feature Extraction from Noisy Image Using PCNN

The entropy sequence of the output image, gotten from the original gray image by pulse-coupled neural network (PCNN), as feature vector of the gray image, can be used as a unique feature expression of gray image, which has been proved by our experiment, therefore, in this paper, it is used in the image classification, and the mean square error (MSE) between the feature vector of the input image and standard feature vector is used to judge the input image belong to which kind of image groups. At the same time, the results of our experiment show that this method is strongly flexible to resist noises and greatly robust to recognize image, if the tested images in our experiment are disturbed with Gaussian noise, impulse noise or both of this

[1]  Reinhard Eckhorn,et al.  Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex , 1990, Neural Computation.

[2]  R. Eckhorn,et al.  High frequency (60-90 Hz) oscillations in primary visual cortex of awake monkey. , 1993, Neuroreport.

[3]  R. Eckhorn,et al.  Stimulus-specific fast oscillations at zero phase between visual areas V1 and V2 of awake monkey. , 1994, Neuroreport.

[4]  Jeffery Johnson,et al.  Pulse coupled neural networks for image processing , 1995, Proceedings IEEE Southeastcon '95. Visualize the Future.

[5]  Heggere S. Ranganath,et al.  Iterative segmentation using pulse-coupled neural networks , 1996, Defense + Commercial Sensing.

[6]  Reinhard Eckhorn,et al.  Size and position invariant visual representation supports retinotopic maps via selective backward paths: A dynamic second order neural network model for a possible functional role of recurrent connections in the visual cortex , 1997, Neurocomputing.

[7]  Eugene M. Izhikevich,et al.  Class 1 neural excitability, conventional synapses, weakly connected networks, and mathematical foundations of pulse-coupled models , 1999, IEEE Trans. Neural Networks.

[8]  Martin Kermit,et al.  Feature extraction from photographic images using a hybrid neural network , 1999, Other Conferences.

[9]  Jason M. Kinser,et al.  Inherent features of wavelets and pulse coupled networks , 1999, IEEE Trans. Neural Networks.

[10]  John L. Johnson,et al.  PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[11]  Heggere S. Ranganath,et al.  Perfect image segmentation using pulse coupled neural networks , 1999, IEEE Trans. Neural Networks.

[12]  Lian Li,et al.  Image segmentation of embryonic plant cell using pulse-coupled neural networks , 2002 .

[13]  Ma Yi-de,et al.  Gaussian noise filter based on PCNN , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[14]  Liu Qing,et al.  Automated image segmentation using improved PCNN model based on cross-entropy , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[15]  Martin Kermit,et al.  Feature extraction from photographical images using a hybrid neural network , 2005 .

[16]  Qi Chun-liang,et al.  Region labeling method based on doublePCNN and morphology , 2005, IEEE International Symposium on Communications and Information Technology, 2005. ISCIT 2005..

[17]  Jason M. Kinser,et al.  Inherent Features of Wavelets and Pulse Coupled Neural Networks , 2007 .