Learned Hyperspectral Compression Using a Student’s T Hyperprior

Hyperspectral compression is one of the most common techniques in hyperspectral image processing. Most recent learned image compression methods have exhibited excellent rate-distortion performance for natural images, but they have not been fully explored for hyperspectral compression tasks. In this paper, we propose a trainable network architecture for hyperspectral compression tasks, which not only considers the anisotropic characteristic of hyperspectral images but also embeds an accurate entropy model using the non-Gaussian prior knowledge of hyperspectral images and nonlinear transform. Specifically, we first design a spatial-spectral block, involving a spatial net and a spectral net as the base components of the core autoencoder, which is more consistent with the anisotropic hyperspectral cubes than the existing compression methods based on deep learning. Then, we design a Student’s T hyperprior that merges the statistics of the latents and the side information concepts into a unified neural network to provide an accurate entropy model used for entropy coding. This not only remarkably enhances the flexibility of the entropy model by adjusting various values of the degree of freedom, but also leads to a superior rate-distortion performance. The results illustrate that the proposed compression scheme supersedes the Gaussian hyperprior universally for virtually all learned natural image codecs and the optimal linear transform coding methods for hyperspectral compression. Specifically, the proposed method provides a 1.51% to 59.95% average increase in peak signal-to-noise ratio, a 0.17% to 18.17% average increase in the structural similarity index metric and a 6.15% to 64.60% average reduction in spectral angle mapping over three public hyperspectral datasets compared to the Gaussian hyperprior and the optimal linear transform coding methods.

Lossy codecs for digital image signatures

Most applications in recent times make use of images one way or the other. As physical devices for capturing images improve, the quality and sizes of images also increase. This causes a significant footprint of images on storage devices. There is ongoing research to reduce the footprint of images on storage. Since storage is a finite resource, the goal is to reduce the sizes of images while maintaining enough quality pleasant to the human eye. In this paper, the design of two lossy codecs for compressing grayscale digital signature images has been presented. The algorithms used either simple thresholding or transform coding to introduce controlled losses into the image coding chain. This was to reduce, to a great extent, the average number of bits per pixel required to represent the images. The codecs were implemented in MATLAB and experiments were conducted with test images to study the performances of the algorithms.

An Efficient Lossless Compression Method for Periodic Signals Based on Adaptive Dictionary Predictive Coding

This paper reports on an efficient lossless compression method for periodic signals based on adaptive dictionary predictive coding. Some previous methods for data compression, such as difference pulse coding (DPCM), discrete cosine transform (DCT), lifting wavelet transform (LWT) and KL transform (KLT), lack a suitable transformation method to make these data less redundant and better compressed. A new predictive coding approach, basing on the adaptive dictionary, is proposed to improve the compression ratio of the periodic signal. The main criterion of lossless compression is the compression ratio (CR). In order to verify the effectiveness of the adaptive dictionary predictive coding for periodic signal compression, different transform coding technologies, including DPCM, 2-D DCT, and 2-D LWT, are compared. The results obtained prove that the adaptive dictionary predictive coding can effectively improve data compression efficiency compared with traditional transform coding technology.