A general memristor-based pulse coupled neural network with variable linking coefficient for multi-focus image fusion

Abstract Pulse coupled neural network (PCNN) is a kind of visual cortex-inspired biological neural network, which has been proved a powerful candidate in the field of digital image processing due to its unique characteristics of global coupling and pulse synchronization. Notably, the inherent parameters estimation issue emerging in the entire system greatly affects the overall network performance. In this paper, a novel memristor crossbar array with its corresponding peripheral circuits is proposed, which is able to construct a general memristor-based PCNN (MPCNN) with variable linking coefficient. In order to verify the effectiveness and generality of the presented network, the single-channel MPCNN is further applied into the multi-focus image fusion problem with an improved multi-channel configuration. Correspondingly, a new type of MPCNN-based image fusion algorithm is put forward along with the design of an appropriate mapping function based on the image orientation information measure. Finally, a series of contrast experiments with comprehensive analysis demonstrate that the proposed fusion method has superior performances in terms of image quality and fusion effect compared to several existing algorithms.

[1]  Paul S. Fisher,et al.  Image quality measures and their performance , 1995, IEEE Trans. Commun..

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

[3]  Yide Ma,et al.  Review of pulse-coupled neural networks , 2010, Image Vis. Comput..

[4]  Sung-Mo Kang,et al.  Resistive Computing: Memristors-Enabled Signal Multiplication , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[5]  Shukai Duan,et al.  Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition , 2015, Neural Computing and Applications.

[6]  Eby G. Friedman,et al.  Synaptic Characteristics of Ag/AgInSbTe/Ta-Based Memristor for Pattern Recognition Applications , 2017, IEEE Transactions on Electron Devices.

[7]  Hyun-Sun Mo,et al.  Time-Shared Twin Memristor Crossbar Reducing the Number of Arrays by Half for Pattern Recognition , 2017, Nanoscale Research Letters.

[8]  Gonzalo Pajares,et al.  A wavelet-based image fusion tutorial , 2004, Pattern Recognit..

[9]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[10]  Mark E. Oxley,et al.  Physiologically motivated image fusion for object detection using a pulse coupled neural network , 1999, IEEE Trans. Neural Networks.

[11]  Shukai Duan,et al.  Multiple Memristor Circuit Parametric Fault Diagnosis Using Feedback-Control Doublet Generator , 2016, IEEE Access.

[12]  Leon O. Chua,et al.  The First Ever Real Bistable Memristors—Part II: Design and Analysis of a Local Fading Memory System , 2016, IEEE Transactions on Circuits and Systems II: Express Briefs.

[13]  Yiran Chen,et al.  Forgetting memristor based neuromorphic system for pattern training and recognition , 2017, Neurocomputing.

[14]  Wei Cai,et al.  An Adaptive Image Segmentation Method Based on a Modified Pulse Coupled Neural Network , 2006, ICNC.

[15]  Farnood Merrikh-Bayat,et al.  3-D Memristor Crossbars for Analog and Neuromorphic Computing Applications , 2017, IEEE Transactions on Electron Devices.

[16]  R. Rakkiyappan,et al.  Impulsive controller design for exponential synchronization of delayed stochastic memristor-based recurrent neural networks , 2016, Neurocomputing.

[17]  Shukai Duan,et al.  Memristor-Based Cellular Nonlinear/Neural Network: Design, Analysis, and Applications , 2015, IEEE Transactions on Neural Networks and Learning Systems.

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

[19]  Jun Li,et al.  Combining singular points and orientation image information for fingerprint classification , 2008, Pattern Recognit..

[20]  Ali Khiat,et al.  Improving Detection Accuracy of Memristor-Based Bio-Signal Sensing Platform , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[21]  Dalibor Biolek,et al.  SPICE Model of Memristor with Nonlinear Dopant Drift , 2009 .

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

[23]  Henk J. A. M. Heijmans,et al.  A new quality metric for image fusion , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

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

[25]  Yide Ma,et al.  A new adaptive filtering method for removing salt and pepper noise based on multilayered PCNN , 2016, Pattern Recognit. Lett..

[26]  Said Hamdioui,et al.  Testing Open Defects in Memristor-Based Memories , 2015, IEEE Transactions on Computers.

[27]  Yide Ma,et al.  Medical image fusion using m-PCNN , 2008, Inf. Fusion.

[28]  Alexander Toet,et al.  Image fusion by a ration of low-pass pyramid , 1989, Pattern Recognit. Lett..

[29]  Vladimir S. Petrovic,et al.  Gradient-based multi-resolution image fusion , 2004 .

[30]  Yide Ma,et al.  A Novel Algorithm of Image Enhancement Based on Pulse Coupled Neural Network Time Matrix and Rough Set , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[31]  J. R. Raol,et al.  Pixel-level Image Fusion using Wavelets and Principal Component Analysis , 2008 .

[32]  Vladimir S. Petrovic,et al.  Gradient-based multiresolution image fusion , 2004, IEEE Transactions on Image Processing.

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

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

[35]  Hui Zhao,et al.  Multi-focus color image fusion in the HSI space using the sum-modified-laplacian and a coarse edge map , 2008, Image Vis. Comput..

[36]  Legeng Chen,et al.  Image fusion algorithm based on spatial frequency-motivated pulse coupled neural networks in Wavelet based contourlet transform domain , 2010, 2010 The 2nd Conference on Environmental Science and Information Application Technology.

[37]  Jinde Cao,et al.  Exponential Synchronization of Coupled Stochastic Memristor-Based Neural Networks With Time-Varying Probabilistic Delay Coupling and Impulsive Delay , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[38]  L. Chua.  Memristor-The missing circuit element , 1971 .

[39]  Ming Zeng,et al.  Feature-preserving filtering with L0 gradient minimization , 2014, Comput. Graph..

[40]  D. Stewart,et al.  The missing memristor found , 2008, Nature.

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

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

[43]  Leon O. Chua,et al.  History Erase Effect in a Non-Volatile Memristor , 2016, IEEE Transactions on Circuits and Systems I: Regular Papers.

[44]  Wen Lu,et al.  On combining visual perception and color structure based image quality assessment , 2016, Neurocomputing.

[45]  Shukai Duan,et al.  Multilayer RTD-memristor-based cellular neural networks for color image processing , 2015, Neurocomputing.

[46]  Qiaoqiao Li,et al.  Feature-Linking Model for Image Enhancement , 2016, Neural Computation.