Infrared and Visual Image Fusion via Multi-modal Decomposition and PCNN in Gradient Domain Fusion Measure

Infrared and visual image fusion aims to obtain a complex image which contains more recognizable information. To obtain the complex image, a fusion algorithm via multi-modal decomposition and pulse-coupled neural network (PCNN) in gradient domain fusion measure is proposed. Firstly, the source images are decomposed into three layers through the decomposition model. Then, a gradient domain PCNN fusion measure is employed in the three layers. Finally, the fused image is reconstructed through the three fused layers. Experimental results demonstrate that the proposed algorithm performs effectively in both qualitative and quantitative measures.

[1]  Juan Du,et al.  A graphical estimation and multiple-sparse representation strategy for hyperspectral anomaly detection , 2019, Infrared Physics & Technology.

[2]  Rui Lai,et al.  Multi-Scale Visual Attention Deep Convolutional Neural Network for Multi-Focus Image Fusion , 2019, IEEE Access.

[3]  Juan Du,et al.  Infrared and visible image perceptive fusion through multi-level Gaussian curvature filtering image decomposition. , 2019, Applied optics.

[4]  Huixin Zhou,et al.  Guided filter and convolutional network based tracking for infrared dim moving target , 2017 .

[5]  Chunhui Zhao,et al.  A fast fusion scheme for infrared and visible light images in NSCT domain , 2015 .

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

[7]  Yu Liu,et al.  A general framework for image fusion based on multi-scale transform and sparse representation , 2015, Inf. Fusion.

[8]  Kun Qian,et al.  Fusion of multi-focus images via a Gaussian curvature filter and synthetic focusing degree criterion. , 2018, Applied optics.

[9]  Yintang Yang,et al.  Spatiotemporal Adaptive Nonuniformity Correction Based on BTV Regularization , 2019, IEEE Access.

[10]  Cedric Nishan Canagarajah,et al.  Pixel- and region-based image fusion with complex wavelets , 2007, Inf. Fusion.

[11]  Yu-Chiang Frank Wang,et al.  Exploring Visual and Motion Saliency for Automatic Video Object Extraction , 2013, IEEE Transactions on Image Processing.

[12]  Shutao Li,et al.  Image Fusion With Guided Filtering , 2013, IEEE Transactions on Image Processing.

[13]  Vladimir Petrovic,et al.  Objective image fusion performance characterisation , 2005, ICCV 2005.

[14]  G. Qu,et al.  Information measure for performance of image fusion , 2002 .

[15]  J. Wesley Roberts,et al.  Assessment of image fusion procedures using entropy, image quality, and multispectral classification , 2008 .

[16]  Huixin Zhou,et al.  Hyperspectral anomaly detection by local joint subspace process and support vector machine , 2020, International Journal of Remote Sensing.

[17]  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.

[18]  Yue Yu,et al.  Multi-focus image fusion using spatial frequency and discrete wavelet transform , 2017, Applied Optics and Photonics China.

[19]  Jun Zhou,et al.  Hyperspectral anomaly detection based on anomalous component extraction framework , 2019, Infrared Physics & Technology.

[20]  Ke Lu,et al.  An overview of multi-modal medical image fusion , 2016, Neurocomputing.

[21]  Yixin Yang,et al.  Hyperspectral Anomaly Detection via Convolutional Neural Network and Low Rank With Density-Based Clustering , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[22]  Ivo F. Sbalzarini,et al.  Curvature Filters Efficiently Reduce Certain Variational Energies , 2017, IEEE Transactions on Image Processing.