Hongda Shen

Hyperspectral imaging (HSI) technology has been used for various remote sensing applications due to its excellent capability of monitoring regions-of-interest over a period of time. However, the large data volume of four-dimensional multitemporal hyperspectral imagery demands massive data compression techniques. While conventional 3D hyperspectral data compression methods exploit only spatial and spectral correlations, we propose a simple yet effective predictive lossless compression algorithm that can achieve significant gains on compression efficiency, by also taking into account temporal correlations inherent in the multitemporal data. We present an information theoretic analysis to estimate potential compression performance gain with varying configurations of context vectors. Extensive simulation results demonstrate the effectiveness of the proposed algorithm. We also provide in-depth discussions on how to construct the context vectors in the prediction model for both multitemporal HSI and conventional 3D HSI data.

For efficient compression of hyperspectral images, we propose a universal Golomb–Rice coding parameter estimation method using deep belief network, which does not rely on any assumption on the distribution of the input data. We formulate the problem of selecting the best coding parameter for a given input sequence as a supervised pattern classification problem. Simulations on the synthesized data and five hyperspectral image datasets show that we can achieve significantly more accurate estimation of the coding parameters, which can translate to slightly higher compression than three state-of-the-art methods. More extensive simulations on additional images from the 2006 AVIRIS datasets show that the proposed method achieved overall compression bitrates comparable with other estimation methods, as well as the sample-adaptive entropy coder employed by the Consultative Committee for Space Data Systems standard for multispectral and hyperspectral data compression. Regarding computational feasibility, we show how to use transferable deep belief networks to speed up training by about five times. We also show that inferring the best coding parameters using a trained deep belief network offers computational advantages over the brute-force search method. As an extension, we propose a novel side-information free codec, where the intersequence correlations can be learned by a differently trained network based on the current sequence to predict reasonably good parameters for coding the next sequence. As another extension, we introduce a variable feature combination architecture, where problem specific heuristics such as the sample means can be incorporated to further improve the estimation accuracy.

While Golomb-Rice codes are optimal for geometrically distributed source, the practically achievable coding efficiency depends on the accuracy of the coding parameter estimated from the input data. Most existing methods are based on the assumption of geometric distribution and thus would suffer from a loss in coding efficiency if the underlying distribution deviates from the geometric distribution, which is usually the case in practice. We proposed a data-driven parameter estimation method without assuming the underlying distribution. We formulated the problem of choosing the best coding parameter for the given input data as a pattern classification problem. To this end, we trained a deep belief network using the data segments to be coded, along with their “labels”, which are the optimal coding parameters that yield the shortest codewords. Simulations on data synthesized using statistical models, as well as data in hyperspectral image coding showed that the proposed deep learning method tended to be more robust than several state-of-the-art parameter estimation methods, with the capability to further improve the accuracies of these methods.

In this paper, we presented an integrated graphical user interface (GUI) tool, which supports interactive regions of interest (ROIs) extraction from whole slide imagery and provides lossless compression of the ROIs extracted, leading to over 40 times compression on the original image. As a case study to demonstrate the usefulness of this tool, we applied a simple block-matching technique to detect malaria infected cells from a whole slide image based on a template provided by the user, who can control the percentage of the extracted pixels by varying the acceptable similarity threshold. The tool allowed us to conduct a comparative study on the efficiencies of several compression methods (including Bzip2, Winzip and Shape-Adaptive JPEG 2000) on image subsets that are continuously variable. This case study provides new insights into the interactions between the geometry of ROIs and the amount of compression achievable on medical images.