Different Types Of Image Data Research Articles

Image Haze Removal Method Based on Histogram Gradient Feature Guidance.

Optical remote sensing images obtained in haze weather not only have poor quality, but also have the characteristics of gray color, blurred details and low contrast, which seriously affect their visual effect and applications. Therefore, improving the image clarity, reducing the impact of haze and obtaining more valuable information have become the important aims of remote sensing image preprocessing. Based on the characteristics of haze images, combined with the earlier dark channel method and guided filtering theory, this paper proposed a new image haze removal method based on histogram gradient feature guidance (HGFG). In this method, the multidirectional gradient features are obtained, the atmospheric transmittance map is modified using the principle of guided filtering, and the adaptive regularization parameters are designed to achieve the image haze removal. Different types of image data were used to verify the experiment. The experimental result images have high definition and contrast, and maintain significant details and color fidelity. This shows that the new method has a strong ability to remove haze, abundant detail information, wide adaptability and high application value.

A Review of Synthetic Image Data and Its Use in Computer Vision.

Development of computer vision algorithms using convolutional neural networks and deep learning has necessitated ever greater amounts of annotated and labelled data to produce high performance models. Large, public data sets have been instrumental in pushing forward computer vision by providing the data necessary for training. However, many computer vision applications cannot rely on general image data provided in the available public datasets to train models, instead requiring labelled image data that is not readily available in the public domain on a large scale. At the same time, acquiring such data from the real world can be difficult, costly to obtain, and manual labour intensive to label in large quantities. Because of this, synthetic image data has been pushed to the forefront as a potentially faster and cheaper alternative to collecting and annotating real data. This review provides general overview of types of synthetic image data, as categorised by synthesised output, common methods of synthesising different types of image data, existing applications and logical extensions, performance of synthetic image data in different applications and the associated difficulties in assessing data performance, and areas for further research.

Real-Time Quality Control in Thin Glass Forming Using Infrared Thermography and Deep Learning

Towards the growing trends in lightweight, flexible, and optical advantages, thin glasses become key components in numerous applications such as consumer electronics like foldable smartphones, or automotive interiors. Nonisothermal glass molding promises a viable technology for the cost-efficient production of precision glass components. In the existing production, the quality of the glass products can only be accessed at the end of the hot forming process. Due to high rates of product failures often appeared in the precision glass molding processes, the current quality control of the produced optical products suffers low process efficiency. This work introduces an enabling approach for monitoring the product quality in real-time using thermography and machine learning. Specifically, the acquisition of the temperature fields of the glass components during the hot forming stage enabled by an infrared thermographic camera allows machine learning to predict the final shape of the molded components at the end of the forming process. Several transfer learning models have been investigated to demonstrate the proposed method. To further enhance the prediction performance, self-built convolutional neural network models were developed using different types of image data. By incorporating the time-series image data as an input to the learning models, the prediction performance was achieved. The model built in the present work demonstrates an excellent prediction accuracy where the difference between the measured and predicted shapes of the glass products can be kept at low double-digit micrometers. Such accuracy achieved by our self-developed machine learning model promisingly satisfy the quality control in serial productions of numerous precision optical glass components in automotive and consumer electronics sectors.

Investigation of Machine Learning Methods for Early Prediction of Neurodevelopmental Disorders in Children

Several variables, for instance, inheritance and surroundings, influence the growth of neurodevelopmental disorders, e.g., autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) during the first 36 months of life. ADHD and ASD diagnosis mainly rely heavily on traditional clinical assessments from the last few decades. These traditional methods are based on massive data collection from multiple respondents’ responses and the extent of various behavioral descriptors, which are then recognized by the researcher while forming a diagnostic criterion. However, opting for traditional diagnostic methods, there is a high possibility of being misdiagnosed, which may lead to the administration of unnecessary long-term pharmaceutical treatment. That may lead to reduction in functioning and an increase in the risk of developing additional social and clinical issues. Moreover, such diagnostic procedures are also time-consuming and costly. In this sense, rapid and advanced criteria are required to be accurate and cost-effective. Consequently, this study emphasizes the application of machine learning (ML) tools and deep learning (DL) techniques such as convolutional neural network (CNN) and Deep Learning APIs (Application Programming Interface), for the early diagnosis and treatment of ADHD and ASD symptoms. From this investigation, it can be concluded that diagnostic techniques based on ML reduce the intervention time and increase the accuracy with simultaneous understanding of the techniques and algorithms applied to different types of Image data. Numerous studies have been done on ASD and ADHD separately, but our investigation also focuses on cooccurrences of these disorders in one individual.

Unsupervised Data Fusion With Deeper Perspective: A Novel Multisensor Deep Clustering Algorithm

The ever-growing developments in technology to capture different types of image data [e.g., hyperspectral imaging and light detection and ranging (LiDAR)-derived digital surface model (DSM)], along with new processing techniques, have led to a rising interest in imaging applications for Earth observation. However, analyzing such datasets in parallel, remains a challenging task. In this article, we propose a multisensor deep clustering (MDC) algorithm for the joint processing of multisource imaging data. The architecture of MDC is inspired by autoencoder (AE)-based networks. The MDC paradigm includes three parallel networks, a spectral network using an autoencoder structure, a spatial network using a convolutional autoencoder structure, and lastly, a fusion network that reconstructs the concatenated image information from the concatenated latent features from the spatial and spectral network. The proposed algorithm combines the reconstruction losses obtained by the aforementioned networks to optimize the parameters (i.e., weights and bias) of all three networks simultaneously. To validate the performance of the proposed algorithm, we use two multisensor datasets from different applications (i.e., geological and rural sites) as benchmarks. The experimental results confirm the superiority of our proposed deep clustering algorithm compared to a number of state-of-the-art clustering algorithms. The code will be available at [Online]. Available: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Kasra2020/MDC</uri> .

Covid-19 Imaging Tools: How Big Data is Big?

In this paper, considering year 2020 and Covid-19, we analyze medical imaging tools and their performance scores in accordance with the dataset size and their complexity. For this, we mainly consider AI-driven tools that employ two different types of image data, namely chest Computed Tomography (CT) and X-ray. We elaborate on their strengths and weaknesses by taking the following important factors into account: i) dataset size; ii) model fitting criteria (over-fitting and under-fitting); iii) transfer learning in the deep learning era; and iv) data augmentation. Medical imaging tools do not explicitly analyze model fitting. Also, using transfer learning, with fewer data, one could possibly build Covid-19 deep learning model but they are limited to education and training. We observe that, in both image modalities, neither the dataset size nor does data augmentation work well for Covid-19 screening purposes because a large dataset does not guarantee all possible Covid-19 manifestations and data augmentation does not create new Covid-19 cases.

Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images.

This study was designed to develop and verify a fully automated cephalometry landmark identification system, based on multi-stage convolutional neural networks (CNNs) architecture, using a combination dataset. In this research, we trained and tested multi-stage CNNs with 430 lateral and 430 MIP lateral cephalograms synthesized by cone-beam computed tomography (CBCT) to make a combination dataset. Fifteen landmarks were manually and respectively identified by experienced examiner, at the preprocessing phase. The intra-examiner reliability was high (ICC = 0.99) in manual identification. The results of prediction of the system for average mean radial error (MRE) and standard deviation (SD) were 1.03 mm and 1.29 mm, respectively. In conclusion, different types of image data might be the one of factors that affect the prediction accuracy of a fully-automated landmark identification system, based on multi-stage CNNs.

A New Approach of Ensemble Learning Technique to Resolve the Uncertainties of Paddy Area through Image Classification

Remote sensing technology has rendered lots of information in agriculture. It has usually been used to monitor paddy growing ecosystems in the past few decades. However, there are uncertainties in data fusion techniques which can be resolved in image classification on paddy rice. In this study, a series of learning concepts integrated by a probability progress Fuzzy Dempster-Shafer (FDS) analysis is presented to upgrade various models and different types of image data which is the goal of this study. More specifically, the study utilized the FDS to generate a series of probability models in the classification of the system. In addition, Logistic Regression (LR), Support Vector Machine (SVM), and Neural Network (NN) approaches are employed into the developed FDS system. Furthermore, two different image types are Satellite Image and Aerial Photo used as the analysis material. The overall classification accuracy has been improved to 97.27%, and the kappa value is 0.93. The overall accuracy of the paddy field image classification for a multi-period of mid-scale satellite images is between 85% and 90%. The overall accuracy of the classification using multi-spectral numerical aerial photos can be between 91% and 95%. The FDS improves the accuracy of the above image classification results.

Improved Software to Browse the Serial Medical Images for Learning.

The thousands of serial images used for medical pedagogy cannot be included in a printed book; they also cannot be efficiently handled by ordinary image viewer software. The purpose of this study was to provide browsing software to grasp serial medical images efficiently. The primary function of the newly programmed software was to select images using 3 types of interfaces: buttons or a horizontal scroll bar, a vertical scroll bar, and a checkbox. The secondary function was to show the names of the structures that had been outlined on the images. To confirm the functions of the software, 3 different types of image data of cadavers (sectioned and outlined images, volume models of the stomach, and photos of the dissected knees) were inputted. The browsing software was downloadable for free from the homepage (anatomy.co.kr) and available off-line. The data sets provided could be replaced by any developers for their educational achievements. We anticipate that the software will contribute to medical education by allowing users to browse a variety of images.

Lossless image compression: application of Bi-level Burrows Wheeler Compression Algorithm (BBWCA) to 2-D data

This research paper demonstrates the robustness of Bi-level Burrows Wheeler Compression Algorithm (BBWCA) in terms of the compression efficiency for different types of image data. The scheme was designed to take advantage of the increased inter-pixel redundancies resulting from a two pass Burrows Wheeler Transformation (BWT) stage and the use of Reversible Colour Transform (RCT). In this research work, BBWCA was evaluated for raster map images, Colour Filter Array (CFA) images as well as 2-D ElectroEncephaloGraphy (EEG) data and compared against benchmark schemes. Validation has been carried out on various examples and they show that BBWCA is capable of compressing 2-D data effectively. The proposed method achieves marked improvement over the existing methods in terms of compression size. BBWCA is 18.8 % better at compressing images as compared to High Efficiency Video Codec (HEVC) and 21.2 % more effective than LZ4X compressor for CFA images. For the EEG data, BBWCA is 17 % better at compressing images as compared to WINRK and 25.2 % more effective than NANOZIP compressor. However, for the Raster images PAQ8 supersedes BBWCA by 11 %. Among the different schemes compared, the proposed scheme achieves overall best performance and is well suited to small and large size image data compression. The parallelization process reduces the execution time particularly for large size images. The parallelized BBWCA scheme reduces the execution time by 31.92 % on average as compared to the non-parallelized BBWCA.

MAPPING RIVER DEPTH FROM PUBLICLY AVAILABLE AERIAL IMAGES

ABSTRACTRemote sensing could facilitate efficient characterization of river systems for research and management purposes, provided that suitable image data are available and that the information derived therefrom is reliable. This study evaluated the utility of public domain multispectral images for estimating flow depths in a small stream and a larger gravel‐bed river, using data acquired through a task‐oriented consortium and the National Agricultural Imagery Program (NAIP). Field measurements were used to calibrate image‐derived quantities to observed depths and to assess depth retrieval accuracy. A band ratio‐based algorithm yielded coherent, hydraulically reasonable bathymetric maps for both field sites and three different types of image data. Applying a spatial filter reduced image noise and improved depth retrieval performance, with a strong calibration relationship (R2 = 0.68) and an observed (field‐surveyed) versus predicted (image‐derived) R2 of 0.6 for tasked images of the smaller stream. The NAIP data were less useful in this environment because of geo‐referencing errors and a coarser spatial resolution. On the larger river, NAIP‐derived bathymetry was more accurate, with an observed versus predicted R2 value of 0.64 for a compressed county mosaic easily accessible via the Internet. Comparison of remotely sensed bathymetric maps with field surveys indicated that although the locations of pools were determined accurately, their full depth could not be detected because of limited sensor radiometric resolution. Although a number of other constraints also must be considered, such as the need for local calibration data, depth retrieval from publicly available image data is feasible under appropriate conditions. Copyright © 2012 John Wiley &amp; Sons, Ltd.

Shape-dependent canny edge detector

Edges characterize the boundaries of objects in images and are informative structural cues for computer vision and target/object detection and recognition systems. The Canny edge detector is widely regarded as the edge detection standard. It is fairly adaptable to different environments, as its parametric nature attempts to tailor the detection of edges based on image-dependent characteristics or the particular requirements of a given implementation. Though it has been used in a myriad of image processing tasks, the Canny edge detector is still vulnerable to edge losses, localization errors, and noise sensitivity. These issues are largely due to the key tradeoff made in the scale and size of the edge detection filters used by the algorithm. Small-scaled filters are sensitive to edges but also to noise, whereas large-scaled filters are robust to noise but could filter out fine details. In this paper, novel edge detection kernel generalizations and a shape-dependent edge detector are introduced to alleviate these shortcomings. While most standard edge detection algorithms are based on convolving the input image with fixed size square kernels, this paper will illustrate the benefits of different filter sizes, and more importantly, different kernel shapes for edge detection. Moreover, new edge fusion methods are introduced to more effectively combine the individual edge responses. Existing edge detectors, including the Canny edge detector, can be obtained from the generalized edge detector by specifying corresponding parameters and kernel shapes. The proposed representations and edge detector have been qualitatively and quantitatively evaluated on several different types of image data. Computer simulations demonstrate that nonsquare kernel approaches can outperform square kernel approaches such as Canny, Sobel, Prewitt, Roberts, and others, providing better tradeoffs between noise rejection, accurate edge localization, and resolution.

JPEG 2000: Get the Bit You Want

JPEG 2000 is an international standard for the compression of still images. Although the new standard provides better compression at any given quality level, the real advantage over the DCT based &#x201C;original&#x201D; JPEG is the feature set. JPEG 2000 can compress different types of image data from black and white graphics to multi-spectral high bit depth imagery at extremely low bit rates or extremely high quality (including lossless). Perhaps more importantly, decisions about compression ratio or quality or region of interest can be made after the image is compressed. This wide range of capabilities make the standard useful in a diverse set of applications including: internet imaging, printing, scanning, digital photography, remote sensing, mobile, color facsimile, medical imagery, and digital libraries.This paper provides a brief overview technologies used in Part I of the standard and sample applications which make use of those features.