A fusion algorithm for infrared and visible images based on adaptive dual-channel unit-linking PCNN in NSCT domain

Abstract In this paper, a novel fusion algorithm based on the adaptive dual-channel unit-linking pulse coupled neural network (PCNN) for infrared and visible images fusion in nonsubsampled contourlet transform (NSCT) domain is proposed. The flexible multi-resolution and directional expansion for images of NSCT are associated with global coupling and pulse synchronization characteristic of dual-PCNN. Compared with other dual-PCNN models, the proposed model possesses fewer parameters and is not difficult to implement adaptive, which is more suitable for image fusion. Firstly, the source images were multi-scale and multi-directional decomposed by NSCT. Then, to make dual-channel PCNN adaptive, the average gradient of each pixel was presented as the linking strength, and the time matrix was presented to determine the iteration number adaptively. In this fusion scheme, a novel sum modified-Laplacian of low-frequency subband and a modified spatial frequency of high-frequency subband were input to motivate the adaptive dual-channel unit-linking PCNN, respectively. Experimental results demonstrate that the proposed algorithm can significantly improve image fusion performance, accomplish notable target information and high contrast, simultaneously preserve rich details information, and excel other typical current methods in both objective evaluation criteria and visual effect.

[1]  Zhongliang Jing,et al.  Evaluation of focus measures in multi-focus image fusion , 2007, Pattern Recognit. Lett..

[2]  Malay Kumar Kundu,et al.  NSCT-based multimodal medical image fusion using pulse-coupled neural network and modified spatial frequency , 2012, Medical & Biological Engineering & Computing.

[3]  Chang Wei-wei.  Fusion algorithm of hyperspectral images based on wavelet transform and multi-channel PCNN , 2011 .

[4]  Minh N. Do,et al.  The Nonsubsampled Contourlet Transform: Theory, Design, and Applications , 2006, IEEE Transactions on Image Processing.

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

[6]  Ashraf K. Helmy,et al.  Image fusion scheme based on modified dual pulse coupled neural network , 2013, IET Image Process..

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

[8]  Yide Ma,et al.  Dual-channel PCNN and Its Application in the Field of Image Fusion , 2007, Third International Conference on Natural Computation (ICNC 2007).

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

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

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

[12]  Aimin Hao,et al.  Multimodal medical image fusion using improved multi-channel PCNN. , 2014, Bio-medical materials and engineering.

[13]  Yi Chai,et al.  Multi-focus image fusion based on nonsubsampled contourlet transform and focused regions detection , 2013 .

[14]  Yang Lei,et al.  Novel fusion method for visible light and infrared images based on NSST–SF–PCNN , 2014 .

[15]  Yi Chai,et al.  Image fusion scheme using a novel dual-channel PCNN in lifting stationary wavelet domain , 2010 .

[16]  Daoheng Yu,et al.  General design approach to unit-linking PCNN for image processing , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[17]  W. Kong,et al.  Image fusion technique based on non-subsampled contourlet transform and adaptive unit-fast-linking pulse-coupled neural network , 2011 .

[18]  Baoshu Li,et al.  An Improved Unit-Linking PCNN for Segmentation of Infrared Insulator Image , 2014 .

[19]  Yide Ma,et al.  A New Algorithm for Noise Reducing of Image Based on PCNN Time Matrix: A New Algorithm for Noise Reducing of Image Based on PCNN Time Matrix , 2011 .

[20]  Xiaodong Gu.  Feature Extraction using Unit-linking Pulse Coupled Neural Network and its Applications , 2007, Neural Processing Letters.

[21]  Tao Men,et al.  Comparison of fusion methods for the infrared and color visible images , 2009, 2009 2nd IEEE International Conference on Computer Science and Information Technology.

[22]  Yide Ma,et al.  Spiking cortical model for multifocus image fusion , 2014, Neurocomputing.

[23]  Cai Xi,et al.  Image fusion algorithm based on adaptive pulse coupled neural networks in curvelet domain , 2010, IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS.

[24]  Chang Wei.  HYPERSPECTRAL MULTI-BAND IMAGE FUSION ALGORITHM BY USING PULSE COUPLED NEURAL NETWORKS , 2010 .

[25]  Xia Jia-xing.  Application and Research Based on Two-channel PCNN , 2012 .

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

[27]  Hadi Seyedarabi,et al.  A non-reference image fusion metric based on mutual information of image features , 2011, Comput. Electr. Eng..

[28]  Minh N. Do,et al.  Ieee Transactions on Image Processing the Contourlet Transform: an Efficient Directional Multiresolution Image Representation , 2022 .

[29]  Y Li.  A Novel Image Fusion Method Using Self-adaptive Dual-channel Pulse Coupled Neural Networks Based on PSO Evolutionary Learning , 2014 .