Abstract
Hyperspectral images (HSIs), which obtain abundant spectral information for narrow spectral bands (no wider than 10 nm), have greatly improved our ability to qualitatively and quantitatively sense the Earth. Since HSIs are collected by high-resolution instruments over a very large number of wavelengths, the data generated by such sensors is enormous, and the amount of data continues to grow, HSI compression technique will play more crucial role in this trend. The classical method for HSI compression is through compression and reconstruction methods such as three-dimensional wavelet-based techniques or the principle component analysis (PCA) transform. In this paper, we provide an alternative approach for HSI compression via a generative neural network (GNN), which learns the probability distribution of the real data from a random latent code. This is achieved by defining a family of densities and finding the one minimizing the distance between this family and the real data distribution. Then, the well-trained neural network is a representation of the HSI, and the compression ratio is determined by the complexity of the GNN. Moreover, the latent code can be encrypted by embedding a digit with a random distribution, which makes the code confidential. Experimental examples are presented to demonstrate the potential of the GNN to solve image compression problems in the field of HSI. Compared with other algorithms, it has better performance at high compression ratio, and there is still much room left for improvements along with the fast development of deep-learning techniques.
Highlights
Hyperspectral remote-sensing technology arose in the 1980s; it can obtain many very narrow and continuous image data in visible, near-infrared, medium, and long-wave infrared spectra
Most feature reduction methods other than deep learning are linear transforms, such as those that use geometric structure [19] to reduce the number of spectral bands and preserve valuable intrinsic information in the Hyperspectral images (HSIs) or approaches based on the wavelet transform to reduce the dimensional space
Since we provide a novel way to compress a HSI, the compression ratio needs to be redefined as the size of the original HSI to the size of the neural network
Summary
Hyperspectral remote-sensing technology arose in the 1980s; it can obtain many very narrow and continuous image data in visible, near-infrared, medium, and long-wave infrared spectra. Dimensionality reduction methods [4,5,6] provide approaches to deal with the computational difficulties of HSIs; these approaches usually use projections to compress a high-dimensional data space into a lower-dimensional space using multiplication by a coefficient matrix. Most feature reduction methods other than deep learning are linear transforms, such as those that use geometric structure [19] to reduce the number of spectral bands and preserve valuable intrinsic information in the HSI or approaches based on the wavelet transform to reduce the dimensional space. A generative neural network (GNN) approximates a continuous function as much as possible, which yields a mapping between the latent space and the data distribution space. The generated image can be as close as possible to the original one if the random latent code, and the GNN can provide enough degrees of freedom. In this paper, GNN stands for generated neural network, which is different from graph neural network
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
