Correlation-based initialization algorithm for tensor-based HSI compression methods

Tensor decomposition (TD) is widely used in hyperspectral image (HSI) compression. we note that the correlation in HSI may be helpful to improve the HSI compression performance of TD methods. The initialization of factor matrix in TD can determine the HSI compression performance. Meanwhile, it is worth noting that HSI is highly correlated in bands. In this paper, we propose a method called correlation-based TD initialization algorithm. By analyzing the optimization of TD, we find that the initialization of TD can be well approximated by a matrix decomposition. Thus, we adopt the mean band of HSI to approximate the initialization of TD. In accordance with the SVD result of the reference band, the initialized factor matrices of TD are produced. We compare our methods with other compression methods. The experimental results reveal that our correlation-based TD initialization method is capable of significantly reducing the computational cost of TD while keeping the initialization quality and compression performance.

[1]  Jiayi Ma,et al.  Hyperspectral Image Classification With Discriminative Kernel Collaborative Representation and Tikhonov Regularization , 2018, IEEE Geoscience and Remote Sensing Letters.

[2]  Cheng Shi,et al.  3D multi-resolution wavelet convolutional neural networks for hyperspectral image classification , 2017, Inf. Sci..

[3]  Xuelong Li,et al.  Hyperspectral biological images compression based on multiway tensor projection , 2014, 2014 IEEE International Conference on Multimedia and Expo (ICME).

[4]  Madheswari Kanmani,et al.  An image contrast enhancement algorithm for grayscale images using particle swarm optimization , 2018, Multimedia Tools and Applications.

[5]  Yechao Bai,et al.  Method for multispectral images denoising based on tensor-singular value decomposition , 2017 .

[6]  Xuelong Li,et al.  A Low-Rank Tensor Decomposition Based Hyperspectral Image Compression Algorithm , 2016, PCM.

[7]  Yukio Kosugi,et al.  Detection and Analysis of the Intestinal Ischemia Using Visible and Invisible Hyperspectral Imaging , 2010, IEEE Transactions on Biomedical Engineering.

[8]  Madheswari Kanmani,et al.  An optimal weighted averaging fusion strategy for thermal and visible images using dual tree discrete wavelet transform and self tunning particle swarm optimization , 2016, Multimedia Tools and Applications.

[9]  Stephen Marshall,et al.  Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries , 2017, Sensors.

[10]  S. Amari,et al.  Nonnegative Matrix and Tensor Factorization [Lecture Notes] , 2008, IEEE Signal Processing Magazine.

[11]  Bin Luo,et al.  Image Representation and Learning With Graph-Laplacian Tucker Tensor Decomposition , 2019, IEEE Transactions on Cybernetics.

[12]  Fábio M. Bayer,et al.  Low-Complexity Multidimensional DCT Approximations for High-Order Tensor Data Decorrelation , 2017, IEEE Transactions on Image Processing.

[13]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[14]  K. Thilagavathi,et al.  An Optimal HSI Image Compression using DWT and CP , 2014 .

[15]  Shuang Wang,et al.  Weighted multifeature hyperspectral image classification via kernel joint sparse representation , 2016, Neurocomputing.

[16]  Jun Huang,et al.  Robust GBM hyperspectral image unmixing with superpixel segmentation based low rank and sparse representation , 2018, Neurocomputing.

[17]  Nikos D. Sidiropoulos,et al.  Tensor Decomposition for Signal Processing and Machine Learning , 2016, IEEE Transactions on Signal Processing.

[18]  Madheswari Kanmani,et al.  Swarm intelligent based contrast enhancement algorithm with improved visual perception for color images , 2017, Multimedia Tools and Applications.

[19]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[20]  Jonathan Cheung-Wai Chan,et al.  Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction , 2019, Remote. Sens..

[21]  Mehran Yazdi,et al.  Compression of Hyperspectral Images Using Discerete Wavelet Transform and Tucker Decomposition , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[22]  Kanmani Madheswari,et al.  Swarm intelligence based optimisation in thermal image fusion using dual tree discrete wavelet transform , 2017 .

[23]  Jon Atli Benediktsson,et al.  Hyperspectral Image Classification via Multiple-Feature-Based Adaptive Sparse Representation , 2017, IEEE Transactions on Instrumentation and Measurement.

[24]  Giovanni Poggi,et al.  Compression of multispectral images by three-dimensional SPIHT algorithm , 2000, IEEE Trans. Geosci. Remote. Sens..

[25]  Deyu Meng,et al.  Compressive Sensing of Hyperspectral Images via Joint Tensor Tucker Decomposition and Weighted Total Variation Regularization , 2017, IEEE Geoscience and Remote Sensing Letters.

[26]  Sofia da Silva Fernandes,et al.  The Initialization and Parameter Setting Problem in Tensor Decomposition-Based Link Prediction , 2017, 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[27]  Bo Du,et al.  Compression of hyperspectral remote sensing images by tensor approach , 2015, Neurocomputing.

[28]  Zilong Liu,et al.  Multispectral Transforms Using Convolution Neural Networks for Remote Sensing Multispectral Image Compression , 2019, Remote. Sens..

[29]  Kala Rajan,et al.  Hyperspectral image compression based on DWT and TD with ALS method , 2016, Int. Arab J. Inf. Technol..