Preservation Of Spatial Information Research Articles

Cross-Modality Image Translation From Brain 18 F-FDG PET/CT Images to Fluid-Attenuated Inversion Recovery Images Using the CypixGAN Framework.

PET/CT and MRI can accurately diagnose dementia but are expensive and inconvenient for patients. Therefore, we aimed to generate synthetic fluid-attenuated inversion recovery (FLAIR) images from 18 F-FDG PET and CT images of the human brain using a generative adversarial network (GAN)-based deep learning framework called the CypixGAN, which combined the CycleGAN framework with the L1 loss function of the pix2pix. Data from 143 patients who underwent PET/CT and MRI were used for training (n = 79), validation (n = 20), and testing (n = 44) the deep learning frameworks. Synthetic FLAIR images were generated using the pix2pix, CycleGAN, and CypixGAN, and white matter hyperintensities (WMHs) were then segmented. The performance of CypixGAN was compared with that of the other frameworks. The CypixGAN outperformed the pix2pix and CycleGAN in generating synthetic FLAIR images with superior visual quality. Peak signal-to-noise ratio and structural similarity index (mean ± standard deviation) estimated using the CypixGAN (20.23 ± 1.31 and 0.80 ± 0.02, respectively) were significantly higher than those estimated using the pix2pix (19.35 ± 1.43 and 0.79 ± 0.02, respectively) and CycleGAN (18.74 ± 1.49 and 0.78 ± 0.02, respectively) ( P < 0.001). WMHs in synthetic FLAIR images generated using the CypixGAN closely resembled those in ground-truth images, as indicated by the low absolute percentage volume differences and high dice similarity coefficients. The CypixGAN generated high-quality FLAIR images owing to the preservation of spatial information despite using unpaired images. This framework may help improve diagnostic performance and cost-effectiveness of PET/CT when MRI scan is unavailable.

Satellite image fusion using cyclic spatio-spectral GAN model

ABSTRACT Preserving spectral and spatial information in the satellite image fusion problem is one of the essential challenges. This paper presents a GAN-based method for fusing panchromatic and multispectral satellite images. The proposed method utilises the idea of Cycle-GAN with two generators, for spectral and spatial information preservation, based on residual in residual dense block super-resolution architecture. First, generator-1 translates panchromatic and multispectral satellite images to a high-resolution fused image and then preserves details by utilising generator-2. The goal is to reach the spatial and spectral details of panchromatic and multispectral satellite images, respectively. Two discriminators are employed, one for spectral and the other for spatial transformations, and weighted L1 loss is used for both as cycle losses. By leveraging the unique capabilities of the two generators, the proposed method achieves high-quality image fusion results with improved spectral and spatial resolutions that are evaluated over two different datasets. The experimental results demonstrate the effectiveness of the proposed method, with enhancements ranging from approximately 2% to 30% and 0.5% to 35% in WorldView2 and GeoEye-1 images, respectively, in five metrics including PSNR. Moreover, we show significant enhancements of approximately 7% to 50% and 22% to 29% in the same datasets in metrics like SAM and ERGAS.

Multiscale Feature-Learning with a Unified Model for Hyperspectral Image Classification.

In the realm of hyperspectral image classification, the pursuit of heightened accuracy and comprehensive feature extraction has led to the formulation of an advance architectural paradigm. This study proposed a model encapsulated within the framework of a unified model, which synergistically leverages the capabilities of three distinct branches: the swin transformer, convolutional neural network, and encoder-decoder. The main objective was to facilitate multiscale feature learning, a pivotal facet in hyperspectral image classification, with each branch specializing in unique facets of multiscale feature extraction. The swin transformer, recognized for its competence in distilling long-range dependencies, captures structural features across different scales; simultaneously, convolutional neural networks undertake localized feature extraction, engendering nuanced spatial information preservation. The encoder-decoder branch undertakes comprehensive analysis and reconstruction, fostering the assimilation of both multiscale spectral and spatial intricacies. To evaluate our approach, we conducted experiments on publicly available datasets and compared the results with state-of-the-art methods. Our proposed model obtains the best classification result compared to others. Specifically, overall accuracies of 96.87%, 98.48%, and 98.62% were obtained on the Xuzhou, Salinas, and LK datasets.

A genetic programming approach to WiFi fingerprint meta-distance learning

Driven by the continuous growth in the number of mobile smart devices, location-based services are becoming a fundamental aspect in the ubiquitous computing domain. In this work, we focus on indoor scenarios, where positioning supports tasks such as navigation, logistics, and access management and control. Most indoor positioning solutions are based on WiFi fingerprinting, thanks to its ease of deployment. Such a technique often requires the adoption of a suitable distance metric to compare the currently observed WiFi access points with those pertaining to fingerprints contained in a database, and whose position is already known. Results from the literature make it evident that classical distance functions among WiFi fingerprints do not preserve spatial information in its entirety. Here, we explore the possibility of addressing such a shortcoming by combining a selection of fingerprint distance functions into a meta-distance, using a genetic programming approach to solve a symbolic regression problem. The outcomes of the investigation, based on 16 publicly available datasets, show that a small, but statistically relevant, improvement can be achieved in preserving spatial information, and that the developed meta-distance has a generalization capability no worse than top-performing classical fingerprint distance functions when trained on a dataset and tested on the others. In addition, when used within a k-nearest-neighbor positioning framework, the meta-distance outperforms all the contenders, despite not being expressly designed to support position estimation. This sheds a light on a significant relationship between preservation of spatial information and localization performance. The achieved results pave the way for the development of more advanced metric learning solutions, that go beyond the limitations of currently-employed fingerprint distance functions.

Spatial feature and resolution maximization GAN for bone suppression in chest radiographs

Background and Objective: Chest radiographs (CXR) are in great demand for visualizing the pathology of the lungs. However, the appearance of bones in the lung region hinders the localization of any lesion or nodule present in the CXR. Thus, bone suppression becomes an important task for the effective screening of lung diseases. Simultaneously, it is equally important to preserve spatial information and image quality because they provide crucial insights on the size and area of infection, color accuracy, structural quality, etc. Many researchers considered bone suppression as an image denoising problem and proposed conditional Generative Adversarial Network-based (cGAN) models for generating bone suppressed images from CXRs. These works do not focus on the retention of spatial features and image quality. The authors of this manuscript developed the Spatial Feature and Resolution Maximization (SFRM) GAN to efficiently minimize the visibility of bones in CXRs while ensuring maximum retention of critical information.Method: This task is achieved by modifying the architectures of the discriminator and generator of the pix2pix model. The discriminator is combined with the Wasserstein GAN with Gradient Penalty to increase its performance and training stability. For the generator, a combination of different task-specific loss functions, viz., L1, Perceptual, and Sobel loss are employed to capture the intrinsic information in the image.Result: The proposed model reported as measures of performance a mean PSNR of 43.588, mean NMSE of 0.00025, mean SSIM of 0.989, and mean Entropy of 0.454 bits/pixel on a test size of 100 images. Further, the combination of δ=104, α=1, β=10, and γ=10 are the hyperparameters that provided the best trade-off between image denoising and quality retention.Conclusion:The degree of bone suppression and spatial information preservation can be improved by adding the Sobel and Perceptual loss respectively. SFRM-GAN not only suppresses bones but also retains the image quality and intrinsic information. Based on the results of student’s t-test it is concluded that SFRM-GAN yields statistically significant results at a 0.95 level of confidence and shows its supremacy over the state-of-the-art models. Thus, it may be used for denoising and preprocessing of images.

Construction and application of quality evaluation index system for remote-sensing image fusion

To objectively and justly compare the results of remote-sensing image fusion, evaluate the fusion algorithm, and optimize the fusion process, a quality evaluation index system is constructed by considering both qualitative and quantitative evaluations. The quantitative evaluation indexes are divided into three types based on the analysis of evaluation methods of the fusion quality of primary remote-sensing images. The applicability and effectiveness of six pixel-level fusion methods of optical remote-sensing image fusion were verified based on the constructed quality evaluation index system used to evaluate those methods in offshore and archipelagic areas. The experimental results indicate that the constructed quality evaluation index system evaluates the fusion algorithm objectively, comprehensively, and accurately. The intensity–hue–saturation transformation-based method distorts spectral features of the original image and easily causes spectrum degradation, whereas the wavelet transformation-based method has an advantage in the preservation of spectral features but efficiently produces blockiness and image penumbrae. The principal component analysis transformation-based method preserves more detailed textures and structural characteristics of original images but loses some physical properties. The Brovey transformation-based method results in spectral distortion, the high pass filter-based method shows a clear boundary of surface features after image fusion, and the Gram–Schmidt-based method shows a high ability of spectral information retention, but the latter performs poorly in the preservation of spatial information. The proposed quality evaluation index system of remote-sensing image fusion can be used as the objective effect evaluation criteria for remote-sensing image fusion and offers a reference for future applications of fusion results.

On the compromise between noise reduction and speech/noise spatial information preservation in binaural speech enhancement.

Spatial information is important for human perception of speech and sound signals. However, this information is often either distorted or completely neglected in noise reduction because it is challenging, to say the least, to achieve optimal noise reduction and accurate spatial information preservation at the same time. This paper studies the problem of binaural speech enhancement. By jointly diagonalizing the speech and noise correlation matrices, we present a method to construct the noise reduction filter as a linear combination of different eigenvectors, which span a certain subspace of the entire space. A different dimension of the subspace gives a different trade-off between noise reduction and speech/noise spatial information preservation. On the one side, if the dimension is equal to 1, maximum noise reduction is achieved but at the price of significant spatial information distortion. On the other extreme, if the dimension of the subspace is equal to that of the entire space, spatial information is accurately preserved but at the cost of no noise reduction. Therefore, one can achieve different levels of compromises between the amount of noise reduction and the level of speech/noise spatial information preservation by adjusting the dimension of the used subspace.

Optical readout studies of the Thick-COBRA gaseous detector

The performance of a Thick-COBRA (THCOBRA) gaseous detector is studied using an optical readout technique. The operation principle of this device is described, highlighting its operation in a gas mixture of Ar/CF4 (80/20 %) for visible scintillation light emission. The contributions to the total gain from the holes and the anode strips as a function of the applied bias voltage were visualized. The preservation of spatial information from the initial ionizations was demonstrated by analyzing the light emission from 5.9 keV X-rays of an 55Fe source. The observed non-uniformity of the scintillation light from the holes supports the claim of a space localization accuracy better than the pitch of the holes. The acquired images were used to identify weak points and sources of instabilities in view of the development of new optimized structures.

Peak-Graph-Based Fast Density Peak Clustering for Image Segmentation

Fuzzy c-means (FCM) algorithm as a traditional clustering algorithm for image segmentation cannot effectively preserve local spatial information of pixels, which leads to poor segmentation results with inconsistent regions. For the remedy, superpixel technologies are applied, but spatial information preservation highly relies on the quality of superpixels. Density peak clustering algorithm (DPC) can reconstruct spatial information of arbitrary-shaped clusters, but its high time complexity $O(n^2)$ and unrobust allocation strategy decrease its applicability for image segmentation. Herein, a fast density peak clustering method (PGDPC) based on the kNN distance matrix of data with time complexity $O(nlog(n))$ is proposed. By using the peak-graph-based allocation strategy, PGDPC is more robust in the reconstruction of spatial information of various complex-shaped clusters, so it can rapidly and accurately segment images into high-consistent segmentation regions. Experiments on synthetic datasets, real and Wireless Capsule Endoscopy (WCE) images demonstrate that PGDPC as a fast and robust clustering algorithm is applicable to image segmentation.

An Approach for the Pan Sharpening of Very High Resolution Satellite Images Using a CIELab Color Based Component Substitution Algorithm

Recent very high spatial resolution (VHR) remote sensing satellites provide high spatial resolution panchromatic (Pan) images in addition to multispectral (MS) images. The pan sharpening process has a critical role in image processing tasks and geospatial information extraction from satellite images. In this research, CIELab color based component substitution Pan sharpening algorithm was proposed for Pan sharpening of the Pleiades VHR images. The proposed method was compared with the state-of-the-art Pan sharpening methods, such as IHS, EHLERS, NNDiffuse and GIHS. The selected study region included ten test sites, each of them representing complex landscapes with various land categories, to evaluate the performance of Pan sharpening methods in varying land surface characteristics. The spatial and spectral performance of the Pan sharpening methods were evaluated by eleven accuracy metrics and visual interpretation. The results of the evaluation indicated that proposed CIELab color-based method reached promising results and improved the spectral and spatial information preservation.

Hyperspectral Pansharpening Based on Spectral Constrained Adversarial Autoencoder

Hyperspectral (HS) imaging is conducive to better describing and understanding the subtle differences in spectral characteristics of different materials due to sufficient spectral information compared with traditional imaging systems. However, it is still challenging to obtain high resolution (HR) HS images in both the spectral and spatial domains. Different from previous methods, we first propose spectral constrained adversarial autoencoder (SCAAE) to extract deep features of HS images and combine with the panchromatic (PAN) image to competently represent the spatial information of HR HS images, which is more comprehensive and representative. In particular, based on the adversarial autoencoder (AAE) network, the SCAAE network is built with the added spectral constraint in the loss function so that spectral consistency and a higher quality of spatial information enhancement can be ensured. Then, an adaptive fusion approach with a simple feature selection rule is induced to make full use of the spatial information contained in both the HS image and PAN image. Specifically, the spatial information from two different sensors is introduced into a convex optimization equation to obtain the fusion proportion of the two parts and estimate the generated HR HS image. By analyzing the results from the experiments executed on the tested data sets through different methods, it can be found that, in CC, SAM, and RMSE, the performance of the proposed algorithm is improved by about 1.42%, 13.12%, and 29.26% respectively on average which is preferable to the well-performed method HySure. Compared to the MRA-based method, the improvement of the proposed method in in the above three indexes is 17.63%, 0.83%, and 11.02%, respectively. Moreover, the results are 0.87%, 22.11%, and 20.66%, respectively, better than the PCA-based method, which fully illustrated the superiority of the proposed method in spatial information preservation. All the experimental results demonstrate that the proposed method is superior to the state-of-the-art fusion methods in terms of subjective and objective evaluations.

Supervised cross-fusion method: a new triplet approach to fuse thermal, radar, and optical satellite data for land use classification

This study presents a new fusion method namely supervised cross-fusion method to improve the capability of fused thermal, radar, and optical images for classification. The proposed cross-fusion method is a combination of pixel-based and supervised feature-based fusion of thermal, radar, and optical data. The pixel-based fusion was applied to fuse optical data of Sentinel-2 and Landsat 8. According to correlation coefficient (CR) and signal to noise ratio (SNR), among the used pixel-based fusion methods, wavelet obtained the best results for fusion. Considering spectral and spatial information preservation, CR of the wavelet method is 0.97 and 0.96, respectively. The supervised feature-based fusion method is a fusion of best output of pixel-based fusion level, land surface temperature (LST) data, and Sentinel-1 radar image using a supervised approach. The supervised approach is a supervised feature selection and learning of the inputs based on linear discriminant analysis and sparse regularization (LDASR) algorithm. In the present study, the non-negative matrix factorization (NMF) was utilized for feature extraction. A comparison of the obtained results with state of the art fusion method indicated a higher accuracy of our proposed method of classification. The rotation forest (RoF) classification results improvement was 25% and the support vector machine (SVM) results improvement was 31%. The results showed that the proposed method is well classified and separated four main classes of settlements, barren land, river, river bank, and even the bridges over the river. Also, a number of unclassified pixels by SVM are very low compared to other classification methods and can be neglected. The study results showed that LST calculated using thermal data has had positive effects on improving the classification results. By comparing the results of supervised cross-fusion without using LST data to the proposed method results, SVM and RoF classifiers showed 38% and 7% of classification improvement, respectively.

Low-delay wind noise cancellation with preservation of spatial information for binaural hearing aids

Low-delay wind noise cancellation with preservation of spatial information for binaural hearing aids

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatch

Since the BOSS competition, in 2010, most steganalysis approaches use a learning methodology involving two steps: feature extraction, such as the Rich Models (RM), for the image representation, and use of the Ensemble Classifier (EC) for the learning step. In 2015, Qian et al. have shown that the use of a deep learning approach that jointly learns and computes the features, was very promising for the steganalysis. In this paper, we follow-up the study of Qian et al., and show that in the scenario where the steganograph always uses the same embedding key for embedding with the simulator in the different images, due to intrinsic joint minimization and the preservation of spatial information, the results obtained from a Convolutional Neural Network (CNN) or a Fully Connected Neural Network (FNN), if well parameterized, surpass the conventional use of a RM with an EC. First, numerous experiments were conducted in order to find the best "shape" of the CNN. Second, experiments were carried out in the clairvoyant scenario in order to compare the CNN and FNN to an RM with an EC. The results show more than 16% reduction in the classification error with our CNN or FNN. Third, experiments were also performed in a cover-source mismatch setting. The results show that the CNN and FNN are naturally robust to the mismatch problem. In Addition to the experiments, we provide discussions on the internal mechanisms of a CNN, and weave links with some previously stated ideas, in order to understand the results we obtained. We also have a discussion on the scenario "same embedding key".

Analysis, evaluation, and comparison of polarimetric SAR speckle filtering techniques.

Speckle noise filtering on polarimetric SAR (PolSAR) images remains a challenging task due to the difficulty to reduce a scatterer-dependent noise while preserving the polarimetric information and the spatial information. This challenge is particularly acute on single look complex images, where little information about the scattering process can be derived from a rank-1 covariance matrix. This paper proposes to analyze and to evaluate the performances of a set of PolSAR speckle filters. The filter performances are measured by a set of ten different indicators, including relative errors on incoherent target decomposition parameters, coherences, polarimetric signatures, point target, and edge preservation. The result is a performance profile for each individual filter. The methodology consists of simulating a set of artificial PolSAR images on which the various filters will be evaluated. The image morphology is stochastic and determined by a Markov random field and the number of scattering classes is allowed to vary so that we can explore a large range of image configurations. Evaluation on real PolSAR images is also considered. Results show that filters performances need to be assessed using a complete set of indicators, including distributed scatterer parameters, radiometric parameters, and spatial information preservation.

Preservation of Spatial Information in Rasterization Processes: A Practical Approach Using Real Categorical Data and Landscape Metrics

Rasterization (i.e., vector-to-raster conversion) is a common process in geographic information systems. As it implies redistribution of map information, it is important to know how much data are lost when a particular resolution is chosen, in order to use data successfully. This study explores the potential of landscape metrics to reflect sensitivity to rasterization processes. A vectorial land use map was rasterized to an array of cell sizes. Deviation from original data was estimated, and landscape metrics were calculated for each land cover class. Results allowed grouping of classes—with respect to how information was preserved—depending on their landscape characteristics.

Dissecting out the genetic origins of Barrett’s oesophagus

Current dogma dating back to the 1970s suggests that the development of cancer occurs through clonal selection such that the primary tumour contains all the genes necessary to invade and...

Subsurface and transcutaneous Raman spectroscopy and mapping using concentric illumination rings and collection with a circular fiber-optic array.

Different spatial separations between an illumination ring and a bundle of 50 collection fibers focused to collect light in the center of the ring were used to investigate the recovery of subsurface Raman spectra. The depth of Raman signal recovery and the preservation of spatial information in the recovered signal were investigated using polymer blocks stacked in different geometries. The illumination rings were then combined into a single data set to increase variation in the signal. Multivariate data analysis was used to recover the Raman spectra of the subsurface component. The Raman spectrum of a Delrin target was recoverable at depths up to 22.6 mm of overlying Teflon. Spatial information was lost at approximately 6.5 mm below the Teflon surface. The same protocols were used to recover canine bone spectra transcutaneously at depths up to 5 mm below the skin's surface. The recovered bone spectra were validated by exposed bone measurements.

The mapping of visual space by identified large second-order neurons in the dragonfly median ocellus

In adult dragonflies, the compound eyes are augmented by three simple eyes known as the dorsal ocelli. The outputs of ocellar photoreceptors converge on relatively few second-order neurons with large axonal diameters (L-neurons). We determine L-neuron morphology by iontophoretic dye injection combined with three-dimensional reconstructions. Using intracellular recording and white noise analysis, we also determine the physiological receptive fields of the L-neurons, in order to identify the extent to which they preserve spatial information. We find a total of 11 median ocellar L-neurons, consisting of five symmetrical pairs and one unpaired neuron. L-neurons are distinguishable by the extent and location of their terminations within the ocellar plexus and brain. In the horizontal dimension, L-neurons project to different regions of the ocellar plexus, in close correlation with their receptive fields. In the vertical dimension, dendritic arborizations overlap widely, paralleled by receptive fields that are narrow and do not differ between different neurons. These results provide the first evidence for the preservation of spatial information by the second-order neurons of any dorsal ocellus. The system essentially forms a one-dimensional image of the equator over a wide azimuthal area, possibly forming an internal representation of the horizon. Potential behavioural roles for the system are discussed.

ENVISAT ASAR Wide Swath and SPOT‐VEGETATION Image Fusion for Wetland Mapping: Evaluation of Different Wavelet‐based Methods

Three wavelet‐based fusion methods (ARSIS, PSIMA and à trous method) are applied to combine ENVISAT ASAR Wide Swath and SPOT‐VEGETATION images. The objectives of the data fusion are feature enhancement and improvement of classification accuracy of a tropical wetland located in the Chad basin, Africa. The fusion results are compared to those obtained by the intensity hue saturation (IHS) method and the principal component (PC) method. Several quantitative tests and a visual inspection are performed to evaluate the different methods. The fused images are classified by means of a maximum likelihood classifier and the classification accuracies are calculated. The results show that the fusion methods based on the wavelet transform perform better then the IHS and PC method for both objectives. From all methods, the ARSIS and the à trous method preserve best the spectral contents of the SPOT‐VEGETATION image. However, the à trous method outperforms the ARSIS method in terms of spatial information preservation. When the PSIMA method is used, artefacts are minimized. The highest classification accuracies are obtained with the PSIMA and à trous methods.