Convolution Neural Network based lossy compression of hyperspectral images

Lossy compression of hyperspectral and ultraspectral images is traditionally performed using 3D transform coding. This approach yields good performance, but the complexity and memory requirements make it unsuitable for onboard compression. In this paper we propose a low-complexity lossy compression scheme based on prediction, quantization and rate-distortion optimization. The scheme employs coset codes coupled with the newconcept of “informed quantization”, and requires no entropy coding. The performance of the resulting algorithm is competitive with that of state-of-the-art 3D transform coding schemes, but the complexity is immensely lower, making it suitable for onboard compression at high throughputs.

To review the literature on lossy compression in dental radiography and to discuss the importance and suitability of the methodology used for evaluation of image compression. A search of Medline (from 1966 to October 2004) was undertaken with the search expression "(Radiography, dental) and compression". Inclusion criterion was that the reference should be evaluating the effect of lossy image compression on diagnostic accuracy. For all included studies, information in relation to mode of image acquisition, image content, image compression, image display, and method of image evaluation was extracted. 12 out of 32 papers were included in the review. The design of these 12 studies was found to vary considerably. Parameters used to express the degree of information loss (DIL) were either or both compression ratio (CR) and compression level (CL). The highest acceptable CR reported in the studies ranged from 3.6% to 15.4%. Furthermore, different CR values were proposed even for the same diagnostic task, for example, for caries diagnosis CR ranged from 6.2% to 11.1%. Lossy image compression can be used in clinical radiology if it does not conflict with national law. However, the acceptable DIL is difficult to express and standardize. CR is probably not suitable to express DIL, because it is image content dependent. CL is also probably not suitable to express DIL because of the lack of compression software standardization.

Hyperspectral sensors are able to provide information that is useful for many different applications. However, the huge amounts of data collected by these sensors are not exempt of drawbacks, especially in remote sensing environments where the hyperspectral images are collected on-board satellites and need to be transferred to the earth’s surface. In this situation, an efficient compression of the hyperspectral images is mandatory in order to save bandwidth and storage space. Lossless compression algorithms have been traditionally preferred, in order to preserve all the information present in the hyperspectral cube for scientific purposes, despite their limited compression ratio. Nevertheless, the increment in the data-rate of the new-generation sensors is making more critical the necessity of obtaining higher compression ratios, making it necessary to use lossy compression techniques. A new transform-based lossy compression algorithm, namely Lossy Compression Algorithm for Hyperspectral Image Systems (HyperLCA), is proposed in this manuscript. This compressor has been developed for achieving high compression ratios with a good compression performance at a reasonable computational burden. An extensive amount of experiments have been performed in order to evaluate the goodness of the proposed HyperLCA compressor using different calibrated and uncalibrated hyperspectral images from the AVIRIS and Hyperion sensors. The results provided by the proposed HyperLCA compressor have been evaluated and compared against those produced by the most relevant state-of-the-art compression solutions. The theoretical and experimental evidence indicates that the proposed algorithm represents an excellent option for lossy compressing hyperspectral images, especially for applications where the available computational resources are limited, such as on-board scenarios.

Hyperspectral image compression has become increasingly important in data exploitation because of enormous data volumes and high redundancy provided by hundreds of contiguous spectral channels. Since a hyperspectral image can be viewed as a 3-dimensional (3D) image cube, many efforts have been devoted to extending 2D image compression techniques to perform 3D image compression on hyperspectral image cubes. Unfortunately, some major issues generally encountered in hyperspectral data exploitation at low or very low-bit rate compression, for example, subpixels and mixed pixels which do not occur in traditional pure pixel-based image compression are often overlooked in such a 2D-to-3D compression. Accordingly, a direct application of 2D-to-3D compression techniques to hyperspectral image cubes without taking precaution may result in significant loss of crucial spectral information provided by subtle substances such as small objects, anomalies during low bit-rate lossy compression. This paper takes a rather different view by investigating lossy hyperspectral compression from a perspective of exploring spectral information, referred to as exploitation-based lossy compression and further develops spectral/spatial hyperspectral image compression to effectively preserve crucial and vital spectral information of objects which are generally missed by commonly used mean-squared error (MSE) or signal-to-noise ratio (SNR)-based compression techniques when lossy compression is performed at low bit rates. In order to demonstrate advantages of the proposed spectral/spatial compression approach applications of subpixel target detection and mixed pixel analysis are used for experiments for performance evaluation.

To assess retrospectively the effect of the Joint Photographic Experts Group 2000 (JPEG2000) compression ratio on the quality of thin-section computed tomographic (CT) images. In this institutional review board-approved investigation (protocol 238/2004), thin-section CT images were subjected to irreversible JPEG2000 compression by using five compression ratios (3:1, 5:1, 7:1, 9:1, and 11:1). Three radiologists independently evaluated 60 thin-section CT images, of various diseases, that were obtained with single-detector (weighted dose index, 14.4 mGy) and multidetector (weighted dose index, 9.8 mGy) CT. Toggling between the original and compressed images, readers had to identify the original image by using a forced-choice two-alternative model and to subjectively rank the quality of what they believed to be the compressed image. To assess the reader's ability to distinguish the compressed from the original image, a binomial test was used. Bonferroni correction was applied for all multiple tests. Images compressed with a ratio of 3:1 were not distinguishable from original images (P > .2 for all readers). With use of the 5:1 ratio, minor differences in appearance between the compressed and original images were seen by one of the three readers. With use of higher compression ratios (>/=7:1), all readers (P < .001) recognized the original image. The quality of more than 90% of the images compressed with a 7:1 or higher ratio was substantially degraded. Single-detector and multidetector CT results were not significantly different. The highest ratio that yielded visually lossless compression of thin-section CT images was 3:1. With the 5:1 ratio, there was minor image quality loss, while use of higher compression ratios (>/=7:1) caused substantial degradation of image quality and potential loss of diagnostic information.

A common problem in applying lossy compression to a hyperspectral image is predicting its effect on spectral target detection performance. Recent work has shown that light amounts of lossy compression can remove noise in hyperspectral imagery that would otherwise bias a covariance-based spectral target detection algorithm’s background-normalized response to target samples. However, the detection performance of such an algorithm is a function of both the specific target of interest as well as the background, among other factors, and therefore sometimes lossy compression operating at a particular compression ratio (CR) will not negatively affect the detection of one target, while it will negatively affect the detection of another. To account for the variability in this behavior, we have developed a target-centric metric that guides the selection of a lossy compression algorithm’s CR without knowledge of whether or not the targets of interest are present in an image. Further, we show that this metric is correlated with the adaptive coherence estimator’s (ACE’s) signal to clutter ratio when targets are present in an image.

In this paper, we evaluate lossless and lossy compression techniques to compress quantitative phase images of red blood cells (RBCs) obtained by an off-axis digital holographic microscopy (DHM). The RBC phase images are numerically reconstructed from their digital holograms and are stored in 16-bit unsigned integer format. In the case of lossless compression, predictive coding of JPEG lossless (JPEG-LS), JPEG2000, and JP3D are evaluated, and compression ratio (CR) and complexity (compression time) are compared against each other. It turns out that JP2k can outperform other methods by having the best CR. In the lossy case, JP2k and JP3D with different CRs are examined. Because some data is lost in a lossy way, the degradation level is measured by comparing different morphological and biochemical parameters of RBC before and after compression. Morphological parameters are volume, surface area, RBC diameter, sphericity index, and the biochemical cell parameter is mean corpuscular hemoglobin (MCH). Experimental results show that JP2k outperforms JP3D not only in terms of mean square error (MSE) when CR increases, but also in compression time in the lossy compression way. In addition, our compression results with both algorithms demonstrate that with high CR values the three-dimensional profile of RBC can be preserved and morphological and biochemical parameters can still be within the range of reported values.

The purpose of this study is to develop hyperspectral imaging (HSI) for automatic detection of head and neck cancer cells on histologic slides. A compact hyperspectral microscopic system is developed in this study. Histologic slides from 15 patients with squamous cell carcinoma (SCC) of the larynx and hypopharynx are imaged with the system. The proposed nuclei segmentation method based on principle component analysis (PCA) can extract most nuclei in the hyperspectral image without extracting other sub-cellular components. Both spectra-based support vector machine (SVM) and patch-based convolutional neural network (CNN) are used for nuclei classification. CNNs were trained with both hyperspectral images and pseudo RGB images of extracted nuclei, in order to evaluate the usefulness of extra information provided by hyperspectral imaging. The average accuracy of spectra-based SVM classification is 68%. The average AUC and average accuracy of the HSI patch-based CNN classification is 0.94 and 82.4%, respectively. The hyperspectral microscopic imaging and classification methods provide an automatic tool to aid pathologists in detecting SCC on histologic slides.

With widespread use of screening digital mammography, efficient storage of the vast amounts of data has become a challenge. While lossless image compression causes no risk to the interpretation of the data, it does not allow for high compression rates. Lossy compression and the associated higher compression ratios are therefore more desirable. The U.S. Food and Drug Administration (FDA) currently interprets the Mammography Quality Standards Act as prohibiting lossy compression of digital mammograms for primary image interpretation, image retention, or transfer to the patient or her designated recipient. Previous work has used reader studies to determine proper usage criteria for evaluating lossy image compression in mammography, and utilized different measures and metrics to characterize medical image quality. The drawback of such studies is that they rely on a threshold on compression ratio as the fundamental criterion for preserving the quality of images. However, compression ratio is not a useful indicator of image quality. On the other hand, many objective image quality metrics (IQMs) have shown excellent performance for natural image content for consumer electronic applications. In this paper, we create a new synthetic mammogram database with several unique features. We compare and characterize the impact of image compression on several clinically relevant image attributes such as perceived contrast and mass appearance for different kinds of masses. We plan to use this database to develop a new objective IQM for measuring the quality of compressed mammographic images to help determine the allowed maximum compression for different kinds of breasts and masses in terms of visual and diagnostic quality.

Hyperspectral (HS) images (HSI) provide a vast amount of spatial and spectral information based on the high dimensionality of the pixels in a wide range of wavelengths. A HS image usually requires massive storage capacity, which demands high compression rates to save space with preservation of data integrity. HS image can be deemed as three dimensional data cube where different wavelengths (W) form the third dimension along with X and Y dimensions. To get a better compression result, spatial redundancy of HS images can be exploited using different coders along X, Y, or W direction. This article focuses on taking maximum advantage of HS images redundancy by rearranging HS image into different 3D data cubes and proposes a directionlet based compression scheme constituted the optimal compression plane (OCP) for adaptive best approximation of geometric matrix. The OCP, calculated by the spectral correlation, is used to the prediction and determination of which reconstructed plane can reach higher compression rates while minimizing data loss of hyperspectral data. Moreover, we also rearrange the 3D data cube into different 2D image planes and investigate the compression ratio using different coders. The schema can be used for both lossless and lossy compression. Our experimental results show that the new framework optimizes the performance of the compression using a number of coding methods (inclusive of lossless/lossy HEVC, motion JPEG, JPG2K, and JPEG) for HSIs with different visual content.KeywordsHyperspectral imageslossless compressionoptimal compression plane (OCP)

&amp;lt;p&amp;gt;The projection into 2030 of the climate data volume increase brings an important challenge to the climate science community. This is particularly true for the CMIP7 that is projected to need about an Exabyte of storage capacity. Error-bounded lossy compression is explored as a potential solution to the above problem by different climate research teams. Several lossy compression schemes have been proposed leveraging different forms of decorrelation (transforms, prediction, HoSVD, DNN), quantization (linear, non-linear, vector), and encoding (dictionary-based, variable length, etc.) algorithms. Our experience with different applications shows that the compression methods often need to be customized and optimized to fit the specificities of the datasets to compress and the user requirements on the compression quality, ratio, and throughput. However, none of the existing lossy compression software for scientific data has been designed to be customizable. To address this issue, we developed SZ3, an innovative customizable, modular compression framework. SZ3 is a full C++ refactoring of SZ2 enabling the specialization, addition, or removal of each stage of the lossy compression pipeline to fit the specific characteristics of the datasets to compress and the use-case requirements. This extreme flexibility allows adapting SZ3 to many different use-cases, from ultra-high compression for visualization to ultra-high-speed compression between the CPU (or GPU) and the memory. Thanks to its unique set of features: customization, high compression ratio, high compression throughput, and excellent accuracy preservation, SZ3 won a 2021 R&amp;amp;D100 award. In this presentation, we present SZ3 and a new data prediction-based decorrelation method that significantly improves the compression ratios for climate datasets over the state-of-the-art lossy compressors, while preserving the same data accuracy. Experiments based on CESM datasets show that SZ3 can lead to up to 300% higher compression ratios than SZ2 with the same compression error bound and similar compression throughput.&amp;lt;/p&amp;gt;

We evaluate the implications of JPEG2000 lossy compression of remote sensing images for spatial analytical purposes. The main issue is to identify which cases and conditions in geostatistical studies are suitable for using lossy compressed images. For these purposes, an extensive test using Landsat, compact airborne spectrographic imager (CASI), and moderate resolution imaging spectroradiometer (MODIS) image series has been analyzed, through applying and comparing two-dimensional and three-dimensional (spectral and time domains) compression methods with a wide range of compression ratios for several dates, different landscape regions, and spectral bands. Due to the massive test bed and consequently to the high time consuming executions, a parallel solution was specifically developed. Variogram analyses showed that all the compression ratios maintain the variogram shapes, but high compression ratios (>20∶1 ) degrade the spatial patterns of the remote sensing images. These alterations are lower for the three-dimensional compression method, which was a considerable improvement (25%) on the two-dimensional method for large three-dimensional series (CASI, MODIS). However, the two methods behave similarly in the Landsat case. Finally, the parallel solution in a distributed environment demonstrates that high performance computing offers a suitable scientific platform for highly demanding time execution applications, such as geostatistical analyses of remote sensing images.

Theoretical and experimental study for enhancement of filtration performance of nonwoven fibrous media by nonuniform compression

The Enhanced Border Security and Visa Entry Reform Act of 2002 requires that the Visa Waiver Program be available only to countries that have a program to issue to their nationals machine-readable passports incorporating biometric identifiers complying with applicable standards established by the International Civil Aviation Organization (ICAO). In June 2002, the New Technologies Working Group of ICAO unanimously endorsed the use of face recognition (FR) as the globally interoperable biometric for machine-assisted identity confirmation with machine-readable travel documents (MRTDs), although Member States may elect to use fingerprint and/or iris recognition as additional biometric technologies. The means and formats are still being developed through which biometric information might be stored in the constrained space of integrated circuit chips embedded within travel documents. Such information will be stored in an open, yet unalterable and very compact format, probably as digitally signed and efficiently compressed images. The objective of this research is to characterize the many factors that affect FR system performance with respect to the legislated mandates concerning FR. A photograph acquisition environment and a commercial face recognition system have been installed at Mitretek, and over 1,400 images have been collected of volunteers. The image database and FR system are being used to analyze the effects of lossy image compression, individual differences, such as eyeglasses and facial hair, and the acquisition environment on FR system performance. Images are compressed by varying ratios using JPEG2000 to determine the trade-off points between recognition accuracy and compression ratio. The various acquisition factors that contribute to differences in FR system performance among individuals are also being measured. The results of this study will be used to refine and test efficient face image interchange standards that ensure highly accurate recognition, both for automated FR systems and human inspectors. Working within the M1-Biometrics Technical Committee of the InterNational Committee for Information Technology Standards (INCITS) organization, a standard face image format will be tested and submitted to organizations such as ICAO.

Today is the digital era and the human being is surrounded by digital gadgets. Now a days, photography is a part of human being's daily life and digital images are widely used in computer applications. As the megapixels of the digital cameras are increasing, more storage memory is required and at the same time more bandwidth is needed for transmission of digital images. This results in need of image compression. This paper explains the use of Legendre polynomials for lossy and lossless image compression. Different approximations for image transformation have been evaluated as 1-D Legendre polynomials, 1-D adaptive Legendre polynomials, 2-D Legendre polynomials and 2-D adaptive Legendre polynomials. Moreover, the performance of different image scanning methods have been tested. Results have been compared in terms of peak signal-to-noise ratio (PSNR), nominal compression rate (NCR), mean structural similarity (MSSIM) and compression ratio in order to minimize the difference between the approximated polynomial output and the original pixel gray level.