PCNN Mechanism and its Parameter Settings

The pulse-coupled neural network (PCNN) model is a third-generation artificial neural network without training that uses the synchronous pulse bursts of neurons to process digital images, but the lack of in-depth theoretical research limits its extensive application. By analyzing the working mechanism of the PCNN, we present an expression for the fire-extinguishing time of neurons that fire in the second iteration and an expression for the firing time of neurons that extinguish in the second iteration. In addition, we find a phenomenon of the PCNN and name it mathematically coupled fire extinguishing. Based on the above analysis, we propose a new working mode for the PCNN, where the refiring of fire-extinguishing neurons is only allowed when all firing neurons are extinguished. We also work out the constraint conditions of the parameter settings under this mode. Furthermore, we analyze the relationship between the network parameters and mathematically coupled fire extinguishing, the coupling of neighboring neurons, and the convergence rate of the PCNN, respectively. In addition, we demonstrate the essential regularity of extinguished neuron in the PCNN and then propose an optimal parameter setting to achieve the best comprehensive performance of the PCNN.

[1]  Karina Waldemark,et al.  Patterns from the sky: Satellite image analysis using pulse coupled neural networks for pre-processing, segmentation and edge detection , 2000, Pattern Recognit. Lett..

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

[3]  Ma,et al.  PCNN Model Analysis and Its Automatic Parameters Determination in Image Segmentation and Edge Detection , 2014 .

[4]  Wei Cai,et al.  Adaptive Parameters Determination Method of Pulse Coupled Neural Network Based on Water Valley Area , 2006, ICONIP.

[5]  Xiaodong Gu.  Classification Using Multi-valued Pulse Coupled Neural Network , 2007, ICONIP.

[6]  Yide Ma,et al.  PCNN Automatic Parameters Determination in Image Segmentation Based on the Analysis of Neuron Firing Time , 2011 .

[7]  Hiroaki Kurokawa,et al.  The Content-Based Image Retrieval using the Pulse Coupled Neural Network , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[8]  Zhang Yi,et al.  A mixed noise image filtering method using weighted-linking PCNNs , 2008, Neurocomputing.

[9]  Roland Olsson,et al.  Automatic design of pulse coupled neurons for image segmentation , 2008, Neurocomputing.

[10]  Ying Zhu,et al.  Multi-focus Image Fusion Based on the Improved PCNN and Guided Filter , 2017, Neural Processing Letters.

[11]  Jyh-Cheng Chen,et al.  An Automatic Segmentation and Classification Framework Based on PCNN Model for Single Tooth in MicroCT Images , 2016, PloS one.

[12]  Wei Liu,et al.  A novel infrared and visible image fusion algorithm based on shift-invariant dual-tree complex shearlet transform and sparse representation , 2017, Neurocomputing.

[13]  Pengfei Xu,et al.  A novel algorithm of remote sensing image fusion based on Shearlets and PCNN , 2013, Neurocomputing.

[14]  Zhen Yang,et al.  A new method of micro-calcifications detection in digitized mammograms based on improved simplified PCNN , 2016, Neurocomputing.

[15]  Yide Ma,et al.  An automatic segmentation method of a parameter-adaptive PCNN for medical images , 2017, International Journal of Computer Assisted Radiology and Surgery.

[16]  Heggere S. Ranganath,et al.  Object detection using pulse coupled neural networks , 1999, IEEE Trans. Neural Networks.

[17]  Xiaodong Gu,et al.  Vehicle License Plate Localization and License Number Recognition Using Unit-Linking Pulse Coupled Neural Network , 2012, ICONIP.

[18]  Wei Cai,et al.  A region-based multi-sensor image fusion scheme using pulse-coupled neural network , 2006, Pattern Recognit. Lett..

[19]  Ke Wang,et al.  Multispectral and Panchromatic Images Fusion by Adaptive PCNN , 2010, MMM.

[20]  Quan Wang,et al.  Multi-focus image fusion method using S-PCNN optimized by particle swarm optimization , 2017, Soft Computing.

[21]  Amr Badr,et al.  An optimized PCNN for image classification , 2014, 2014 10th International Computer Engineering Conference (ICENCO).

[22]  Sarat Kumar Sahoo,et al.  Pulse coupled neural networks and its applications , 2014, Expert Syst. Appl..

[23]  Yu Sun,et al.  Automated color image edge detection using improved PCNN model , 2008 .

[24]  Zhen Yang,et al.  A new method of detecting micro-calcification clusters in mammograms using contourlet transform and non-linking simplified PCNN , 2016, Comput. Methods Programs Biomed..

[25]  Hua Jiang,et al.  Catenary image segmentation using the simplified PCNN with adaptive parameters , 2018 .

[26]  Bangjun Lei,et al.  Multiplicative decomposition based image contrast enhancement method using PCNN factoring model , 2014, Proceeding of the 11th World Congress on Intelligent Control and Automation.

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

[28]  Yide Ma,et al.  Leaf recognition based on PCNN , 2015, Neural Computing and Applications.

[29]  Chao Gao,et al.  Automatic iterative algorithm for image segmentation using a modified pulse-coupled neural network , 2013, Neurocomputing.

[30]  Yide Ma,et al.  A New Automatic Parameter Setting Method of a Simplified PCNN for Image Segmentation , 2011, IEEE Transactions on Neural Networks.

[31]  Zhihui Wang,et al.  A multi-faceted adaptive image fusion algorithm using a multi-wavelet-based matching measure in the PCNN domain , 2017, Appl. Soft Comput..

[32]  Ma Yi-de,et al.  PCNN Model Automatic Parameters Determination and Its Modified Model , 2012 .

[33]  Yide Ma,et al.  Region-Based Object Recognition by Color Segmentation Using a Simplified PCNN , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[34]  Zhang Yi,et al.  A class of binary images thinning using two PCNNs , 2007, Neurocomputing.

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

[36]  Randy P. Broussard.  Physiologically-Based Vision Modeling Applications and Gradient Descent-Based Parameter Adaptation of Pulse Coupled Neural Networks , 1997 .

[37]  Yide Ma,et al.  Self-adaptive autowave pulse-coupled neural network for shortest-path problem , 2013, Neurocomputing.

[38]  Li Yan,et al.  A fusion algorithm for infrared and visible images based on adaptive dual-channel unit-linking PCNN in NSCT domain , 2015 .

[39]  Yi Chai,et al.  Multifocus image fusion scheme based on features of multiscale products and PCNN in lifting stationary wavelet domain , 2011 .

[41]  Zhen Yang,et al.  Saliency motivated improved simplified PCNN model for object segmentation , 2018, Neurocomputing.

[42]  Guanying Wang,et al.  Pulse-coupled neural networks and parameter optimization methods , 2017, Neural Computing and Applications.

[43]  S. Shajun Nisha,et al.  Noise Removal in Medical Images Using Pulse Coupled Neural Networks , 2017 .

[44]  Jason Jianjun Gu,et al.  Multi-focus image fusion using PCNN , 2010, Pattern Recognit..

[45]  Zhang Yi,et al.  Real-Time Robot Path Planning Based on a Modified Pulse-Coupled Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[46]  Dongguo Zhou,et al.  Region growing for image segmentation using an extended PCNN model , 2017, IET Image Process..

[47]  Chong Shen,et al.  Hybrid image noise reduction algorithm based on genetic ant colony and PCNN , 2017, The Visual Computer.

[48]  Hong Zhou,et al.  Simplified parameters model of PCNN and its application to image segmentation , 2015, Pattern Analysis and Applications.

[49]  Jason M. Kinser,et al.  Finding the shortest path in the shortest time using PCNN's , 1999, IEEE Trans. Neural Networks.

[50]  Shukai Duan,et al.  Memristive pulse coupled neural network with applications in medical image processing , 2017, Neurocomputing.

[51]  Ashraf K. Helmy,et al.  Image segmentation scheme based on SOM-PCNN in frequency domain , 2016, Appl. Soft Comput..