Image Data Sources Research Articles

Learning from imbalanced COVID-19 chest X-ray (CXR) medical imaging data.

The trendy task of digital medical image analysis has been continually evolving. It has been an area of prominent and growing importance from both research and deployment perspectives. Nonetheless, it is necessary to realize that the use of algorithms, methodology, as well as the source of medical image data, must be strictly scrutinized. As the COVID-19 pandemic has been gripping much of the world recently, there has been much efforts gone into developing affordable testing for the masses, and it has been shown that the established and widely available chest X-rays (CXR) images may be used as a screening criteria for assistive diagnosis purpose. Thanks to the dedicated work by various individuals and organizations, publicly available CXR of COVID-19 subjects are available for analytic usage. We have also provided a publicly available CXR dataset on the Kaggle platform. As a case study, this paper presents a systematic approach to learn from a typically imbalanced set of CXR images, which consists of a limited number of publicly available COVID-19 images. Our results show that we are able to outperform the top finishers in a related Kaggle multi-class CXR challenge. The proposed methodology should be able to help guide medical personnel in obtaining a robust diagnosis model to discern COVID-19 from other conditions confidently.

Block compressive sensing chaotic embedded encryption for MCF-OFDM transmission system.

In this paper, we propose a block compressive sensing (BCS) based chaotic embedded encryption scheme for multi-core fiber orthogonal frequency division multiplexing (MCF-OFDM) system. BCS technology is used to recover the entire desired information from the small amounts of data. Meanwhile, a four-dimensional discrete chaotic encryption model generates four masking factors, which are respectively used for coefficient random permutation (CRP), measurement matrix, diffusion and singular value decomposition (SVD) embedding to achieve ultra-high security encryption of four different dimensions. In terms of compressive sensing, CRP can make the discrete cosine transform (DCT) coefficient distribute randomly to improve the sampling efficiency of BCS. Compared with the data without compressive sensing, the data volume is reduced by 75%. In chaotic encryption, SVD technology embeds secret images of noise-like after initial encryption into carrier images to generate encrypted images with visual security. The key space reaches 10120 and it realizes the dual protection of source image data and external representation. The proposed scheme using a 2km 7-core optical fiber achieves a 78.75 Gb/s transmission of encrypted OFDM signals. The received optical power is greater than -14 dBm, and the bit error rate (BER) of core1-core7 is lower than 10-3. When the compression ratio sets to 0.25 and the attack range of encrypted data is up to 30%, the image can still recover the outline and general information. The experimental results show that this scheme can improve the security performance and reduce the complexity of information transmission system. Furthermore, the scheme combines The BCS chaotic embedded encryption technology with MCF-OFDM system, which has a good application prospect in the future optical networks.

Emerging artificial intelligence methods for fighting lung cancer: A survey

Lung cancer has one of the highest incidence rates and mortality rates among all common cancers worldwide. Early detection of suspicious lung nodules is crucial in fighting lung cancer. In recent years, with the proliferation of clinical data like low-dose computed tomography (LDCT), histology whole slide images, electronic health records, and sensor readings from medical IoT devices etc., many artificial intelligence tools have taken more important roles in lung cancer management. In this survey, we lay out the current and emergent artificial intelligence methods for fighting lung cancers. Besides the commonly used CT image based deep learning models for detecting and diagnosing lung nodules, we also cover emergent AI techniques for lung cancer: 1) federated deep learning models for harnessing multi-center data with privacy in mind, 2) multi-modal deep learning models for integrating multiple sources of clinical and image data, 3) interpretable deep learning models for opening the black box for clinicians. In the big data era for cancer management, we believe this short survey will help AI researchers better understand the clinical challenges of lung cancer and will also help clinicians better understand the emergent AI tools.

Cafe market share using satellite image data and Google Database in Malang City

Cafes in Malang City have a very large quantity. Almost every main road corridor in Malang City has a small, medium, or large cafe. In a competitive situation, location factors can be critical, making it very important. Therefore, a study is needed to analyze the market share of cafes in Malang City from its spatial elements. This study aims to determine the spatial factors that affect the market share of cafes based on sample data in the form of upper-middle-class cafes in Malang City. The variables used to measure the market share of the café sample spatially are proximity to universities, building density, road hierarchy, rating, and several competitors. This study uses Google Satellite Image Data sources and remote sensing methods for processing spatial data and analyzes it using Multiple Linear Regression Analysis. Based on the analysis results, it is known that all variables are positive. The variables that have the most influence on the market share of the café sample are building density, university proximity, and road hierarchy

Simulation of remote sensing satellite motion base on two line element sets for search and rescue at sea.

Nowadays, satellite remote sensing technology has been applied in many fields of socio-economic development, including search and rescue at sea. Systems with the integration of remote sensing satellite technology have made the search and rescue operations faster, more accurate and more efficient. With the search and rescue systems at sea, remote sensing satellite motion simulation is an important task. This helps the authorities to identify and select the appropriate remote sensing satellite image data source to assist in processing and zoning search and rescue at sea. However, in Vietnam, it is difficult to determine the satellite image data source for the search and rescue situations. Therefore, the research team built a remote sensing satellite motion simulation program based on two-line element data. This is the data source that has been used in astronomy research. This program will simulate satellite orbits in real time and at any time. The accuracy evaluation result of satellite orbit simulation have been compared with online remote sensing satellite tracking systems in the world. The research result show that the satellite orbit simulation has ensured accuracy.

A Transformer-Based Coarse-to-Fine Wide-Swath SAR Image Registration Method under Weak Texture Conditions

As an all-weather and all-day remote sensing image data source, SAR (Synthetic Aperture Radar) images have been widely applied, and their registration accuracy has a direct impact on the downstream task effectiveness. The existing registration algorithms mainly focus on small sub-images, and there is a lack of available accurate matching methods for large-size images. This paper proposes a high-precision, rapid, large-size SAR image dense-matching method. The method mainly includes four steps: down-sampling image pre-registration, sub-image acquisition, dense matching, and the transformation solution. First, the ORB (Oriented FAST and Rotated BRIEF) operator and the GMS (Grid-based Motion Statistics) method are combined to perform rough matching in the semantically rich down-sampled image. In addition, according to the feature point pairs, a group of clustering centers and corresponding images are obtained. Subsequently, a deep learning method based on Transformers is used to register images under weak texture conditions. Finally, the global transformation relationship can be obtained through RANSAC (Random Sample Consensus). Compared with the SOTA algorithm, our method’s correct matching point numbers are increased by more than 2.47 times, and the root mean squared error (RMSE) is reduced by more than 4.16%. The experimental results demonstrate that our proposed method is efficient and accurate, which provides a new idea for SAR image registration.

Multi-Temporal Data Fusion in MS and SAR Images Using the Dynamic Time Warping Method for Paddy Rice Classification

This study employed a data fusion method to extract the high-similarity time series feature index of a dataset through the integration of MS (Multi-Spectrum) and SAR (Synthetic Aperture Radar) images. The farmlands are divided into small pieces that consider the different behaviors of farmers for their planting contents in Taiwan. Hence, the conventional image classification process cannot produce good outcomes. The crop phenological information will be a core factor to multi-period image data. Accordingly, the study intends to resolve the previous problem by using three different SPOT6 satellite images and nine Sentinel-1A synthetic aperture radar images, which were used to calculate features such as texture and indicator information, in 2019. Considering that a Dynamic Time Warping (DTW) index (i) can integrate different image data sources, (ii) can integrate data of different lengths, and (iii) can generate information with time characteristics, this type of index can resolve certain classification problems with long-term crop classification and monitoring. More specifically, this study used the time series data analysis of DTW to produce “multi-scale time series feature similarity indicators”. We used three approaches (Support Vector Machine, Neural Network, and Decision Tree) to classify paddy patches into two groups: (a) the first group did not apply a DTW index, and (b) the second group extracted conflict predicted data from (a) to apply a DTW index. The outcomes from the second group performed better than the first group in regard to overall accuracy (OA) and kappa. Among those classifiers, the Neural Network approach had the largest improvement of OA and kappa from 89.51, 0.66 to 92.63, 0.74, respectively. The rest of the two classifiers also showed progress. The best performance of classification results was obtained from the Decision Tree of 94.71, 0.81. Observing the outcomes, the interference effects of the image were resolved successfully by various image problems using the spectral image and radar image for paddy rice classification. The overall accuracy and kappa showed improvement, and the maximum kappa was enhanced by about 8%. The classification performance was improved by considering the DTW index.

Urban Building Mesh Polygonization Based on 1-Ring Patch and Topology Optimization

With the development of UAV and oblique photogrammetry technology, the multi-view stereo image has become an important data source for 3D urban reconstruction, and the surface meshes generated by it have become a common way to represent the building surface model due to their high geometric similarity and high shape representation ability. However, due to the problem of data quality and lack of building structure information in multi-view stereo image data sources, it is a huge challenge to generate simplified polygonal models from building surface meshes with high data redundancy and fuzzy structural boundaries, along with high time consumption, low accuracy, and poor robustness. In this paper, an improved mesh representation strategy based on 1-ring patches is proposed, and the topology validity is improved on this basis. Experimental results show that our method can reconstruct the concise, manifold, and watertight surface models of different buildings, and it can improve the processing efficiency, parameter adaptability, and model quality.

Multi-focus Source Images Reconstruction based on Adaptive Regional Data Hiding

Preserving the information of multi-focus source images was neglected in previous image fusion schemes since source image data discarding will happen during the fusion process. Data hiding technology can utilize the redundant bits to embed essential secret data. Inspired from that we proposed a multi-focus image reconstruction algorithm using adaptive regional data hiding. Integrating the Human Visual System (HVS) into the reconstruction module, we further proposed a visual grayscale information entropy operator, which is implemented to segment fused images into texture and flat regions for adaptive data hiding after unfocused region data compression. Our method achieves excellent performances in reconstruction Peak signal-to-noise Ratio (PSNR) above 43dB and maintains the satisfying visual effect of the fused images.

End-to-end Modeling for Predicting and Estimating Radiomics: Application to Gray Level Co-occurrence Matrices in CT.

While radiomics models are finding increased use in computer-aided diagnostics and as imaging biomarkers for inference and discovery, their utility in computed tomography (CT) is limited by variability of the image properties produced by different CT scanners, imaging protocols, patient anatomy, and an increasingly diverse range of reconstruction and post-processing software. While these effects can be mitigated with careful data curation and standardization of protocols, this is impractical for diverse sources of image data. In this work, we propose to generalize traditional end-to-end imaging system models to include radiomics calculation as an explicit stage. Such a model permits both prediction of the undesirable variability of radiomics, but also forms a basis for inverting the process to estimate the true underlying radiomics. This framework has the potential to provide for standardization of radiomics across imaging conditions permitting more widespread application of radiomics models; larger, more diverse image databases; and improved diagnoses and inferences based on those standardized metrics. We apply this framework to a large class of popular radiomics based on the Gray Level Co-occurrence matrix under conditions of imaging system that are well describe by traditional linear systems approaches as well as nonlinear systems for which traditional analytic models do not apply.

Introducing Image Classification Efficacies

Accuracy assessment is essential in all image classification-related fields, ranging from molecular imaging to earth observation. However, existing accuracy metrics are too sensitive to class imbalance or lack explicit interpretations for assessing classification performance. Consequently, their scores may be misleading when they are applied to compare classification algorithms that address different image data sources. These limitations jeopardize the widespread application of deep learning classification methods for classifying different image types. We introduce the metrics of image classification efficacy from medicine and pharmacology to overcome the limitations of accuracy metrics. We include a baseline classification to derive the metrics of image classification efficacy and apply real-world and hypothetical examples to further examine their usefulness. Image classification efficacies can be applied at the map and class levels and for binary and multiclass classifications. The interpretability and comparability of image classification efficacies facilitate reliable classification method evaluation across data sources. We detail the procedures of classification efficacy assessment for image classification researchers and classifier users.

Deep Domain Adaptation Based Multi-Spectral Salient Object Detection

Salient Object Detection (SOD) plays an important role in many image-related multimedia applications. Although there are many existing research works about the salient object detection in traditional RGB (visible-light spectrum) images, there are still many complex situations that regular RGB images cannot provide enough cues for the accurate SOD, such as the shadow effect, similar appearance between background and foreground, strong or insufficient illumination, etc. Because of the success of near-infrared spectrum in many computer vision tasks, we explore the multi-spectral SOD in the synchronized RGB images and near-infrared (NIR) images for the both simple and complex situations. We assume that the RGB SOD in the existing RGB image datasets could provide references for the multi-spectral SOD problem. In this paper, we mainly model this research problem as a deep learning based domain adaptation from the traditional RGB image data (source domain) to the multi-spectral data (target domain), and an adversarial deep domain adaptation model is proposed. We first collect and will publicize a large multi-spectral dataset, RGBN-SOD dataset, including 780 synchronized RGB and NIR image pairs for the multi-spectral SOD problem in the simple and complex situations. Intensive experimental results show the effectiveness and accuracy of the proposed deep domain adaptation for the multi-spectral SOD. Besides, due to the absence of research on the field of multi-spectral co-saliency detection, we also collect 200 synchronized RGB and NIR image pairs in addition to explore the multi-spectral co-saliency detection.

Exploration of nature-based biomimetic approach in landscape architectural design: parametric study of candelabra model design

This research provides an exploration of a biomimetic approach in the process of designing a candelabra model using linear shaped leaves of a Bell flower. The design process described in this research contains two steps: biological and geometrical. In the first biological step, a proper model for the creation of an urban element was found from nature in a Bell flower (Campanula persicifolia L.). The upper leaves of the selected plant, which are small with a linear spear and sharpening at the top, were chosen for the modeling process. The second step included applying two geometrical methods, i.e., Voronoi diagrams and Delaunay triangulation. A geometrical leaf form of the selected plant species and the modeling process were obtained using aparametric modeling software, Blender. Using different Blender plug-ins and modifiers, Delaunay triangulation and Voronoi diagram were implemented by marking the starting points on the leaf form in the image data source, adjusting the Delaunay triangulation parameters, and creating Voronoi diagrams in which the Voronoi points were located at the shortest distance from the edges of the Voronoi polygon. Consequently, a three dimensional model of a candelabra was developed through this study.

Survey on performance of deep learning models for detecting road damages using multiple dashcam image resources

Detecting road damage quickly and accurately facilitates the ability of road-maintenance agencies to make timely repairs to road surfaces, maintain optimal road conditions, optimize transportation safety, and minimize transportation costs. An extensive evaluation of eight deep-learning-based road-damage detection models was conducted in this study. Each model was trained on 9493 images sourced from multiple databases. The 16165 instances of road damage in these images were categorized into five types of damage, including longitudinal crack, horizontal crack, alligator damage, pothole-related crack, and line blurring. Two experiments were conducted that identified two models, single shot multi-box detector (SSD) Inception V2 and faster region-based convolutional neural networks (R-CNN) Inception V2, as providing the best balance of road-damage-detection accuracy and image processing time. These experiments demonstrated that increasing the diversity of image sources improved road-damage-detection model performance. In addition to combining data images from different sources with consistently relabeled damage instances, this study released road-damage image data from the road maintenance agency in Zhubei, Hsinchu County, Taiwan for research and other uses, increasing the limited amount of published image data sources and positively impacting future scholarly research into road damage detection.

Current Applications, Opportunities, and Limitations of AI for 3D Imaging in Dental Research and Practice.

The increasing use of three-dimensional (3D) imaging techniques in dental medicine has boosted the development and use of artificial intelligence (AI) systems for various clinical problems. Cone beam computed tomography (CBCT) and intraoral/facial scans are potential sources of image data to develop 3D image-based AI systems for automated diagnosis, treatment planning, and prediction of treatment outcome. This review focuses on current developments and performance of AI for 3D imaging in dentomaxillofacial radiology (DMFR) as well as intraoral and facial scanning. In DMFR, machine learning-based algorithms proposed in the literature focus on three main applications, including automated diagnosis of dental and maxillofacial diseases, localization of anatomical landmarks for orthodontic and orthognathic treatment planning, and general improvement of image quality. Automatic recognition of teeth and diagnosis of facial deformations using AI systems based on intraoral and facial scanning will very likely be a field of increased interest in the future. The review is aimed at providing dental practitioners and interested colleagues in healthcare with a comprehensive understanding of the current trend of AI developments in the field of 3D imaging in dental medicine.

Modelling 3D Topography by Comparing Airborne Lidar Data with Unmanned Aerial System (UAS) Photogrammetry Under Multiple Imaging Conditions

This study presents the effect of image data sources on the topographic modelling of part of the National Trust site located at Weston-Super-Mare, Bristol, United Kingdom, covering an approximate area of 1.82 hectares. The accuracy of the DEM generated from 1m resolution and 2m resolution LiDAR data together with the accuracy of the DEM generated from the UAV images acquired at different altitudes are analysed using the 1 m LiDAR DEM as reference for the accuracy assessment. Using the NSSDA methodology, the horizontal and vertical accuracy of the DEMs generated from each of the four sources were computed while the paired sample t-test was conducted to ascertain the existence of statistically significant difference between the means of the X, Y, and Z coordinates of the check points. The result obtained shows that with a RMSE of -0.0101499 and horizontal accuracy of -0.175674686m, the planimetric coordinates extracted from 2 m LiDAR DEM were more accurate than the planimetric coordinates extracted from the UAV based DEMs while the UAV based DEMs proved to be more accurate than the 2m LiDAR DEM in terms of altimetric coordinates, though the DEM generated from UAV images acquired at 50 m altitude gave the most accurate result when compared with the vertical accuracy obtained from the DEM generated from UAV images acquired at 30 m and 70 m flight heights. These findings are also consistent with the result of the statistical analysis at 95% confidence interval.

Improvement and Application Analysis of Lake Water Body Tracking and Recognition Algorithm

Basing on 30 years’ historical image data sources of Sanshan Lake between 1986 and 2017, this paper proposes a water body tracking and recognition algorithm according to the complex water area features of the lake and its branches to conduct the extraction of the historical water surface area and analysis on influence factors of Sanshan Lake. Comparing to conventional image extraction methods such as the region growing algorithm and the two-pass scanning method, this method shows its advantage of being fast and accurate. By analysing the water surface variation law of Sanshan Lake in 30 years and the influence factors, the area of Sanshan Lake is found to show a significant attenuation trend with the annual average attenuation rate reaches 0.98%; the water surface area weakly correlated with the precipitation change; the lake shore waterline line retreated 0.3- 10 meters in the 30 years; the pond and farmland area increased by 133%, indicating that the regulation of the lake water body is more affected by the lake shoreline dike and the Regulating capacity of gate pump.

Mining Ground Surface Information Extraction and Topographic Analysis Using UAV Video Data

Taking the Xiangwang bauxite mining of Xiaoyi City, Shanxi Province as the research object, the DJi “Wu”inspire2 model Unmanned aerial vehicle (UAV) was used to obtain the video data, image data and Ground control points (GCP) data of a typical pit in the study area. Based on the two kinds of data source (video data and image data), the Digital surface model (DSM) of the research area was acquired with or without ground control points through aerial triangulation and block adjustment. Using the DSM obtained by the two data source, the distribution of elevation, slope, slope direction, surface fluctuation and surface roughness was extracted and compared. Research shows that the DSM, acquired by the ContextCapture software without GCP, using video data obtained by aerial shooting around one interest point, can qualitatively reflect the topographic distribution of the land surface. The DSM got by the video data with the GCP can achieve the similar accuracy with the result obtained by image data, and the topographic information acquired by the two kinds of data source has highly similar characteristics in spatial and numerical distribution. It can be concluded through comparison and analysis of the topographical factors that steep slopes with complex topography and large elevation difference distributes in the northwest-central of the pit, of which northwest and southwest slopes can be easily eroded by wind and rain, so attention should be paid to slop stability monitoring and disaster prevention in this area. As a whole, the results show that video data obtained by UAV can not only reflect the dynamic changes of the land surface qualitatively, but also can describe the distribution of surface topography quantitatively through processing to get the DSM. It has great application potential in the field of disaster emergency monitoring and geological hazard risk assessment in mining areas.

Digital image processing and spectral data source in seed analysis

Abstract Image processing is currently gaining lots of attention at seed quality labs as well as grain quality labs for being nondestructive, faster, and more objective than traditional seed or grain analysis methods. While seed analysts focus on quality parameters that will ensure vigorous plants, grain analysts focus on parameters related to safety or grading of the grain using roughly the same methods. We observed that few techniques on image processing have been used and that image data source roughly shapes research work done. The main data sources are visible light, hyperspectral imaging in the infrared section, and X-ray. Laser speckle is not so common but was also included. We have also noted that ultrasound imaging and magnetic resonance are also used for analysis, but these data sources were left out because of little work found.

Application of Improved Non-local Mean Filtering Algorithm in Detection of Oil and Gas Wells

As the oil and gas exploration in most parts of China has entered into the middle and late stages, the aging and wear problems of mining equipment have become increasingly prominent. In the process of visual image acquisition of oil and gas well casing damage, due to the influence of the complex environment of light and dust, the image data source noise is serious, and the image recognition model has low accuracy. This paper improves the neighbourhood filtering algorithm block search process with the ant colony pheromone correlation theory, optimizes the block matching process with the Pearson algorithm, and eventually applies the optimized non-local mean filtering algorithm to the oil and gas well casing damage visual detection process. The experimental results show that the improved non-local mean filtering algorithm has a significant impact on the adaptability and effectiveness of the noise reduction effect.