Large Size Images Research Articles

A modular architecture for high resolution image dehazing

Haze is an atmospheric phenomenon which diminishes visibility in outdoor images. Algorithms based on dark channel prior (DCP) and haze line prior are found to be effective for dehazing images. These two methods make use of the Laplacian matrix, which is computationally complex, memory intensive and slow, thus making it impossible to use them on high-resolution (large) images. Multiple strategies have been suggested in the literature to speed up dehazing process by avoiding the Laplacian matrix, but these methods compromise on the quality of dehazing. We propose an effective modular method which divides the input image into blocks and processes each block independently. This makes it possible to use our method for dehazing large images retaining Laplacian matting and thus ensuring the output image quality. This division results in the possibility of assuming local values of atmospheric light. We show that this approach results in better dehazing in the local regions. The effectiveness of the proposed modular architecture is tested also on a learning based method. The output of the modular method is compared with those of different state-of-the-art dehazing methods for multiple quality parameters. Toward this, we have created a dataset of hazy natural outdoor images of large size.

ГЕОДЕЗІЯ, КАРТОГРАФІЯ І АЕРОФОТОЗНІМАННЯ

Aim. Determination of the elements of external spatial orientation of the surveying systems at the moment of image acquisition is the fundamental task in photogrammetry. Principally, this problem is solving in two ways. The first way is direct positioning and measuring of directions of camera optical axis in the geodetic space with the help of GNSS/INS equipment. The second way is the analytical solution of the problem using a set of reference information (often such information is a set of ground control points whose geodetic positions are known with sufficient accuracy and which are reliably recognised on aerial images of the photogrammetric block). The authors consider the task of providing reference and control information using the second approach, which has a number of advantages in terms of reliability and accuracy of determining the unknown image exterior orientation parameters. It is proposed to obtain additional images of ground control points by the method of their auxiliary aerial photography using an unmanned aerial vehicle (UAV) on a larger scale compared to the scale of the images of the photogrammetric block. The aim of the presented work is the implementation of the method of creating reference points and experimental confirmation of its effectiveness for photogrammetric processing. Methods and results. For the entire realization of the potential of the analytical way to determine the elements of external orientation of images, it is necessary to have a certain number of ground control points (GCP) and to keep the defined scheme of their location on the photogrammetric block. As the main source of input data authors use UAV aerial images of the terrain, which are obtained separately from the block of aerial survey, and have a better geometric resolution and which clearly depict the control reference points. Application of such auxiliary images gives the possibility of automated transferring of the position of ground control point into images of the main photogrammetric block. In our interpretation, these images of ground control points and their surroundings on the ground are called "control reference images". The basis of the work is to develop a method for obtaining the auxiliary control reference images and transferring of position of GCP depicted on them into aerial or space images of terrain by means of computer stereo matching. To achieve this goal, we have developed a processing method for the creation of control reference images of aerial image or a series of auxiliary multi-scale aerial images obtained by a drone from different heights above the reference point. The operator identifies and measures the GCP once on the auxiliary aerial image of the highest resolution. Then there is an automatic stereo matching of the control reference image in the whole series of auxiliary images in succession with a decrease in the resolution and, ultimately, directly with the aerial images of photogrammetric block. On this stage there are no recognition/cursor targeting by the human operator, and therefore there are no discrepancies, errors or mistakes related to it. In addition, if to apply fairly large size of control reference images, the proposed method can be used on a low-texture terrain, and therefore deal in many cases without the physical marking of points measured by GNSS method. And this is a way to simplify and reduce the cost of photogrammetric technology. The action of the developed method has been verified experimentally to provide the control reference information of the block of archival aerial images of the low-texture terrain. The results of the experimental approbation of the proposed method give grounds to assert that the method makes it possible to perform geodetic reference of photogrammetric projects more efficiently due to the refusal of the physical marking of the area before aerial survey. The proposed method can also be used to obtain the information for checking the quality of photogrammetric survey for provision of check points. The authors argue that the use of additional equipment - UAV of semi-professional class to obtain control reference images is economically feasible. Scientific novelty and practical relevance. The results of approbation of the "control reference image" method with obtaining stereo pairs of aerial images with vertical placement of the base are presented for the first time. There was implemented the study of the properties of such stereo pairs of aerial images to obtain images of reference points. The effectiveness of including reference images in the main block of the digital aerial triangulation network created on UAV’s images is shown.

Single-pixel pattern recognition with coherent nonlinear optics

In this Letter, we propose and experimentally demonstrate a nonlinear-optics approach to pattern recognition with single-pixel imaging and a deep neural network. It employs mode-selective image up-conversion to project a raw image onto a set of coherent spatial modes, whereby its signature features are extracted optically in a nonlinear manner. With 40 projection modes, the classification accuracy reaches a high value of 99.49% for the modified national institute of standards and technology handwritten digit images, and up to 95.32%, even when they are mixed with strong noise. Our experiment harnesses rich coherent processes in nonlinear optics for efficient machine learning, with potential applications in online classification of large-size images, fast lidar data analyses, complex pattern recognition, and so on.

Penerapan Algoritma Punctured Elias Codes Dalam Kompresi Citra

In the process of managing multiple images or images, with larger image sizes or images that can hold longer storage and larger storage, it is needed more often as it cannot be contained on storage media and is not conveyed, thus opening up free space in memory storage media. So to make a lot of free space and have a data size that is not large on the storage media, a compression method is needed which means to shorten the required bit size. Punctured Elias Algorithm Code can be used to obtain information about the compression performed by compressing images to provide benefits in storage and requires more memory space compared to uncompressed images.

Compression of multi-temporal hyperspectral images based on RLS filter

The large-scale acquisition of multi-temporal hyperspectral images has increased the demand for a more efficient compression strategy to reduce the large size of such images. In this work, we propose a lossless prediction-based compression technique for multi-temporal images. It removes temporal correlations along with spatial and spectral correlation, reducing the size of time-lapse hyperspectral image significantly. It predicts the pixel value of the target image by a linear combination of pixels from already predicted spectral and temporal bands. The weight matrix used in the prediction is updated using the RLS filter. Experimental results demonstrate the optimal number of bands to be selected for prediction, the comparative strength of individual correlations, and effectiveness of the technique in terms of bit-rate. Our results show that including temporal correlations reduces the bit-rate by 24.07% and our model provides optimization of 18.15% in terms of bits per pixel compared to the state-of-the-art method.

Background dominant colors extraction method based on color image quick fuzzy c-means clustering algorithm

A quick and accurate extraction of dominant colors of background images is the basis of adaptive camouflage design. This paper proposes a Color Image Quick Fuzzy C-Means (CIQFCM) clustering algorithm based on clustering spatial mapping. First, the clustering sample space was mapped from the image pixels to the quantized color space, and several methods were adopted to compress the amount of clustering samples. Then, an improved pedigree clustering algorithm was applied to obtain the initial class centers. Finally, CIQFCM clustering algorithm was used for quick extraction of dominant colors of background image. After theoretical analysis of the effect and efficiency of the CIQFCM algorithm, several experiments were carried out to discuss the selection of proper quantization intervals and to verify the effect and efficiency of the CIQFCM algorithm. The results indicated that the value of quantization intervals should be set to 4, and the proposed algorithm could improve the clustering efficiency while maintaining the clustering effect. In addition, as the image size increased from 128 × 128 to 1024 × 1024, the efficiency improvement of CIQFCM algorithm was increased from 6.44 times to 36.42 times, which demonstrated the significant advantage of CIQFCM algorithm in dominant colors extraction of large-size images.

Wavelet-transform-based speckle vector tracking method for X-ray phase imaging.

We introduce a new X-ray speckle-vector tracking method for phase imaging, which is based on the wavelet transform. Theoretical and experimental results show that this method, which is called wavelet-transform-based speckle-vector tracking (WSVT), has stronger noise robustness and higher efficiency compared with the cross-correlation-based method. In addition, the WSVT method has the controllable noise reduction and can be applied with fewer scan steps. These unique features make the WSVT method suitable for measurements of large image sizes and phase shifts, possibly under low-flux conditions, and has the potential to broaden the applications of speckle tracking to new areas requiring faster phase imaging and real-time wavefront sensing, diagnostics, and characterization.

Memory-efficient GAN-based domain translation of high resolution 3D medical images

Generative adversarial networks (GANs) are currently rarely applied on 3D medical images of large size, due to their immense computational demand. The present work proposes a multi-scale patch-based GAN approach for establishing unpaired domain translation by generating 3D medical image volumes of high resolution in a memory-efficient way.The key idea to enable memory-efficient image generation is to first generate a low-resolution version of the image followed by the generation of patches of constant sizes but successively growing resolutions. To avoid patch artifacts and incorporate global information, the patch generation is conditioned on patches from previous resolution scales. Those multi-scale GANs are trained to generate realistically looking images from image sketches in order to perform an unpaired domain translation. This allows to preserve the topology of the test data and generate the appearance of the training domain data.The evaluation of the domain translation scenarios is performed on brain MRIs of size 155 × 240 × 240 and thorax CTs of size up to 5123. Compared to common patch-based approaches, the multi-resolution scheme enables better image quality and prevents patch artifacts. Also, it ensures constant GPU memory demand independent from the image size, allowing for the generation of arbitrarily large images.

Assessing the Influence of OCT-A Device and Scan Size on Retinal Vascular Metrics.

PurposeThe purpose of this study was to investigate the effect of device and scan size on quantitative optical coherence tomography angiography (OCT-A) metrics.MethodsThe 3 × 3 mm scans from Optovue AngioVue and Zeiss AngioPlex systems were included for 18 eyes of 18 subjects without ocular pathology. The foveal avascular zone (FAZ) was segmented manually by two observers, from which estimates of FAZ area (using both the nominal image scale and the axial length corrected image scale) and acircularity were derived. Three scan sizes (3 mm, 6 mm HD, and 8 mm) from the AngioVue system were included for 15 eyes of 15 subjects without ocular pathology. For each subject, larger image sizes were resized to the same resolution as 3 × 3 mm scans, aligned, then cropped to a common area. FAZ area, FAZ acircularity, average and total parafoveal intercapillary area, vessel density, and vessel end points were computed.ResultsBetween the devices used here, there were no significant differences in FAZ acircularity (P = 0.88) or FAZ area using scaled (P = 0.11) or unscaled images (P = 0.069). Although there was no significant difference in FAZ area across scan sizes (P = 0.30), vessel morphometry metrics were all significantly influenced by scan size.ConclusionsThe scan devices and sizes used here do not affect FAZ area measures derived from manual segmentations. In contrast, vessel morphometry metrics are affected by scan size. As individual differences in axial length induce differences in absolute scan size, extreme care should be taken when interpreting metrics of vessel morphometry, both between and within OCT-A devices.Translational RelevanceA better characterization of the confounds surrounding OCT-A retinal vasculature metrics can lead to improved application of these metrics as biomarkers for retinal and systemic diseases.

A novel CAD system to automatically detect cancerous lung nodules using wavelet transform and SVM

A novel cancerous nodules detection algorithm for computed tomography images (CT-images) is presented in this paper. CT-images are large size images with high resolution. In some cases, number of cancerous lung nodule lesions may missed by the radiologist due to fatigue. A CAD system that is proposed in this paper can help the radiologist in detecting cancerous nodules in CT- images. The proposed algorithm is divided to four stages. In the first stage, an enhancement algorithm is implement to highlight the suspicious regions. Then in the second stage, the region of interest will be detected. The adaptive SVM and wavelet transform techniques are used to reduce the detected false positive regions. This algorithm is evaluated using 60 cases (normal and cancerous cases), and it shows a high sensitivity in detecting the cancerous lung nodules with TP ration 94.5% and with FP ratio 7 cluster/image.

Comprehensive review of hyperspectral image compression algorithms

Rapid advancement in the development of hyperspectral image analysis techniques has led to specialized hyperspectral missions. It results in the bulk transmission of hyperspectral images from sensors to analysis centers and finally to data centers. Storage of these large size images is a critical issue that is handled by compression techniques. This survey focuses on different hyperspectral image compression algorithms that have been classified into two broad categories based on eight internal and six external parameters. In addition, we identified research challenges and suggested future scope for each technique. The detailed classification used in this paper can categorize other compression algorithms and may help in selecting research objectives.

A Large Size Image Classification Method Based on Semi-supervised Learning

Background: Semi-supervised learning in the machine learning community has received widespread attention. Semi-supervised learning can use a small number of tagged samples and a large number of untagged samples for efficient learning. Methods: In 2014, Kim proposed a new semi-supervised learning method: the minimax label propagation (MMLP) method. This method reduces time complexity to O (n), with a smaller computation cost and stronger classification ability than traditional methods. However, classification results are not accurate in large-scale image classifications. Thus, in this paper, we propose a semisupervised image classification method, which is an MMLP-based algorithm. The main idea is threefold: (1) Improving connectivity of image pixels by pixel sampling to reduce the image size, at the same time, reduce the diversity of image characteristics; (2) Using a recall feature to improve the MMLP algorithm; (3) through classification mapping, gaining the classification of the original data from the classification of the data reduction. Results: In the end, our algorithm also gains a minimax path from untagged samples to tagged samples. The experimental results proved that this algorithm is applicable to semi-supervised learning on small-size and that it can also gain better classification results for large-size image at the same time. Conclusion: In our paper, considering the connectivity of the neighboring matrix and the diversity of the characteristics, we used meanshift clustering algorithm, next we will use fuzzy energy clustering on our algorithm. We will study the function of these paths.

Efficient extraction of pore networks from massive tomograms via geometric domain decomposition

Image-based modelling of porous media to study the transport and reaction processes has become an essential tool. The availability of increasingly large image datasets at high resolution creates a need to develop algorithms that can process massive size images at a low computational cost. This study presents an efficient workflow to extract pore networks from large size porous domains using a watershed segmentation with geometrical domain decomposition. The method subdivides a porous image into smaller overlapping subdomains and performs a watershed segmentation on each subdomain in parallel or serial modes of operation to save CPU time or memory RAM, respectively. The computational performance of the algorithm was analyzed on a large size image and found to consume 50 percent less memory and upto 7 times less CPU time than the standard watershed implementation. Pore networks of four massive digital rock images were extracted and the the effective permeability predicted by the networks agreed well with previously investigated values illustrating the accuracy of the method. An additional application of this method, taking advantage of the reduced computational cost, is the upgrading of low-resolution image. It was found that increasing the resolution of a coarse image leads to more accurate predictions by helping the watershed segmenation prouduce a more faithful pore network model. The developed algorithm is implemented in Python, and included in the open source project PoreSpy. It uses highly optimized and efficient modules such as Dask and Numba to obtain the maximum performance. The domain decomposition approach used here will also lend itself well to processing on distributed memory clusters, enabling the processing of even larger porous domains.

MFALNet: A Multiscale Feature Aggregation Lightweight Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Semantic segmentation labels each pixel in high-resolution remote sensing (HRRS) images with a category. To tackle with the large size and complexity of HRRS images, this letter presents a novel multiscale feature aggregation lightweight network (MFALNet) for semantic segmentation. Unlike standard convolution, asymmetric depth-wise separable convolution residual (ADCR) unit is used to reduce the parameter size of the network and makes the optimized structure deeper but lightweight and less complex. The proposed network is an encoder–decoder structure, where multiscale feature aggregation is implemented in both the encoder and the decoder. The spatial self-attention block helps to capture long-range contextual information, and the gated convolution modules are further used for refining features when aggerating high- and low-level feature maps in the decoder. The proposed MFALNet has evaluated on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam 2-D semantic labeling contest open benchmark data set, and the experimental results prove that the scheme can obtain a better tradeoff between segmentation accuracy and computational efficiency compared with the state-of-the-art semantic segmentation models.

GLOBAL MESSAGE PASSING IN NETWORKS VIA TASK-DRIVEN RANDOM WALKS FOR SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGES

Abstract. The capability of globally modeling and reasoning about relations between image regions is crucial for complex scene understanding tasks such as semantic segmentation. Most current semantic segmentation methods fall back on deep convolutional neural networks (CNNs), while their use of convolutions with local receptive fields is typically inefficient at capturing long-range dependencies. Recent works on self-attention mechanisms and relational reasoning networks seek to address this issue by learning pairwise relations between each two entities and have showcased promising results. But such approaches have heavy computational and memory overheads, which is computationally infeasible for dense prediction tasks, particularly on large size images, i.e., aerial imagery. In this work, we propose an efficient method for global context modeling in which at each position, a sparse set of features, instead of all features, over the spatial domain are adaptively sampled and aggregated. We further devise a highly efficient instantiation of the proposed method, namely learning RANdom walK samplIng aNd feature aGgregation (RANKING). The proposed module is lightweight and general, which can be used in a plug-and-play fashion with the existing fully convolutional neural network (FCN) framework. To evaluate RANKING-equipped networks, we conduct experiments on two aerial scene parsing datasets, and the networks can achieve competitive results at significant low costs in terms of the computational and memory.

Identifying the axillary nerve during shoulder surgery: an anatomic study using advanced imaging

BackgroundThe axillary nerve (AXN) is one of the more commonly injured nerves during shoulder surgery. Prior anatomic studies of the AXN in adults were performed using cadaveric specimens with small sample sizes. Our research observes a larger cohort of magnetic resonance imaging (MRI) studies in order to gain a more representative sample of the course of the AXN and aid surgeons intraoperatively.MethodsHigh-resolution 3T MRI studies performed at our institution from January 2010 to June 2019 were reviewed. Four blinded reviewers with musculoskeletal radiology or orthopedic surgery training measured the distance of the AXN to the surgical neck of the humerus (SNH), the lateral tip of the acromion (LTA), and the inferior glenoid rim (IGR). Intraclass correlation coefficient was calculated to assess reliability between reviewers. The nerve location was assessed relative to rotator cuff tear status.ResultsA total of 257 shoulder MRIs were included. Intraclass correlation coefficient was excellent at 0.80 for the SNH, 0.90 for the LTA, and 0.94 for the IGR. All intraobserver reliabilities were above 0.80. The mean distance from the AXN to SNH was 1.7 cm (range, 0.7-3.1 cm; interquartile range, 1.38-2.00) and that from the AXN to IGR was 1.6 cm (range, 0.6-2.6 cm; interquartile range, 1.33-1.88). The mean AXN to LTA distance was 7.1 cm, with a range of 5.2-9.0 cm across patient heights; there was a large effect size related to the LTA to AXN distance and patient height with a correlation of r = 0.603 (P < .001). Rotator cuff pathology appears to affect nerve location by increasing the distance between the AXN and SNH (P = .027).Discussion/ConclusionThe AXN is vulnerable to injury during both open and arthroscopic shoulder procedures. This injury can be either a result of direct trauma to the nerve or secondary to traction placed on the nerve with reconstructive procedures that distalize the humerus. Our study demonstrates that the AXN can be found as little as 5.6 mm from the IGR and 6.9 mm from the SNH. In addition, we illustrate the relationship between patient height and the LTA to AXN distance and complete rotator cuff tears and the SNH to AXN distance. Our study is the first to demonstrate the nerve's proximity to important surgical landmarks of the shoulder using a large sample size of high-resolution images in living human shoulders.

Multi‐head mutual‐attention CycleGAN for unpaired image‐to‐image translation

The image-to-image translation, i.e. from source image domain to target image domain, has made significant progress in recent years. The most popular method for unpaired image-to-image translation is CycleGAN. However, it always cannot accurately and rapidly learn the key features in target domains. So, the CycleGAN model learns slowly and the translation quality needs to be improved. In this study, a multi-head mutual-attention CycleGAN (MMA-CycleGAN) model is proposed for unpaired image-to-image translation. In MMA-CycleGAN, the cycle-consistency loss and adversarial loss in CycleGAN are still used, but a mutual-attention (MA) mechanism is introduced, which allows attention-driven, long-range dependency modelling between the two image domains. Moreover, to efficiently deal with the large image size, the MA is further improved to the multi-head mutual-attention (MMA) mechanism. On the other hand, domain labels are adopted to simplify the MMA-CycleGAN architecture, so only one generator is required to perform bidirectional translation tasks. Experiments on multiple datasets demonstrate MMA-CycleGAN is able to learn rapidly and obtain photo-realistic images in a shorter time than CycleGAN.

Kompresi Gambar dengan Transformasi Wavelet

Current technological developments have increased quite rapidly, one of which is in digital image processing. The use of digital images sometimes experience problems during the upload process or when users want to insert image files on a platform but are limited by the maximum image file size. The image file to be uploaded must go through a digital image processing so that the image file size can match the requested maximum limit. One technique that can be used in this problem is compression. Compression is one of the main techniques of image processing. Large image size results in reduced data or memory storage. So that compression is also carried out to reduce the use of data storage and hence communication costs. There are many methods used in image compression today. One method used is to use wavelet transforms. In this research, the mother wavelet used is the Biorthogonal wavelet. The purpose of this study is to find out how much the accuracy of the Biorthogonal wavelet to be implemented in color images and to determine the image quality and performance of the Biorthogonal wavelet function in image compression. Decomposition levels used in this study are level 1, level 2, and level 3. The results of the study are displayed in the form of images before compression and image compression results, equipped with PSNR, MSE values, compression ratio, and the size of the compressed images.

Deep-Hipo: Multi-scale receptive field deep learning for histopathological image analysis.

Digitizing whole-slide imaging in digital pathology has led to the advancement of computer-aided tissue examination using machine learning techniques, especially convolutional neural networks. A number of convolutional neural network-based methodologies have been proposed to accurately analyze histopathological images for cancer detection, risk prediction, and cancer subtype classification. Most existing methods have conducted patch-based examinations, due to the extremely large size of histopathological images. However, patches of a small window often do not contain sufficient information or patterns for the tasks of interest. It corresponds that pathologists also examine tissues at various magnification levels, while checking complex morphological patterns in a microscope. We propose a novel multi-task based deep learning model for HIstoPatholOgy (named Deep-Hipo) that takes multi-scale patches simultaneously for accurate histopathological image analysis. Deep-Hipo extracts two patches of the same size in both high and low magnification levels, and captures complex morphological patterns in both large and small receptive fields of a whole-slide image. Deep-Hipo has outperformed the current state-of-the-art deep learning methods. We assessed the proposed method in various types of whole-slide images of the stomach: well-differentiated, moderately-differentiated, and poorly-differentiated adenocarcinoma; poorly cohesive carcinoma, including signet-ring cell features; and normal gastric mucosa. The optimally trained model was also applied to histopathological images of The Cancer Genome Atlas (TCGA), Stomach Adenocarcinoma (TCGA-STAD) and TCGA Colon Adenocarcinoma (TCGA-COAD), which show similar pathological patterns with gastric carcinoma, and the experimental results were clinically verified by a pathologist. The source code of Deep-Hipo is publicly available athttp://dataxlab.org/deep-hipo.

Impact of image analysis and artificial intelligence in thyroid pathology, with particular reference to cytological aspects.

Thyroid pathology has great potential for automated/artificial intelligence algorithm application as the incidence of thyroid nodules is increasing and the indeterminate interpretation rate of fine-needle aspiration remains relatively high. The aim of the study is to review the published literature on automated image analysis and artificial intelligence applications to thyroid pathology with whole-slide imaging. Systematic search was carried out in electronic databases. Studies dealing with thyroid pathology and use of automated algorithms applied to whole-slide imaging were included. Quality of studies was assessed with a modified QUADAS-2 tool. Of 919 retrieved articles, 19 were included. The main themes addressed were the comparison of automated assessment of immunohistochemical staining with manual pathologist's assessment, quantification of differences in cellular and nuclear parameters among tumour entities, and discrimination between benign and malignant nodules. Correlation coefficients with manual assessment were higher than 0.76 and diagnostic performance of automated models was comparable with an expert pathologist diagnosis. Computational difficulties were related to the large size of whole-slide images. Overall, the results are promising and it is likely that, with the resolution of technical issues, the application of automated algorithms in thyroid pathology will increase and be adopted following suitable validation studies.