Histogram Segmentation Research Articles

An efficient ranking-based data-driven model for ship inspection optimization

Maritime safety and environmental protection are fundamental considerations within the shipping industry. In this context, port state control (PSC) inspection is globally implemented by port authorities as a mechanism to enforce both maritime safety standards and environmental regulations. This study proposes an innovative optimization framework based on machine learning (ML) and operations research models for high-risk vessel selection, aiming to maximize the efficiency and effectiveness of PSC inspection. The essence of the optimization framework is to accurately rank all ships with respect to their risk levels predicted by ML models. The loss functions of the tailored ML models follow a “smart predict then optimize” (SPO) criterion named cumulative detected deficiency number (CDDN), which is motivated by the characteristics of the decision problem. This inventive measurement transforms the assessment of ranking accuracy to the area of the segmented histogram of the recognized deficiency number, which bypasses the computationally intensive training step of rankings and is easy to compute. Following this, three types of decision tree (DT) models are developed, which differ from each other in the varying integration levels of CDDN. Particularly, we rigorously prove that one integration method yields a tree structure identical to that of traditional DT models. The proposed models are validated and compared with the traditional DT model on different scales of instances from real inspection records at the Hong Kong port. The experiment results indicate that our tailored DT models improve the ship selection efficiency significantly when the decision is complex, i.e., when we need to optimize the selection of a small number of ships for inspection from a large number of foreign visiting ships. Moreover, we also extensively discuss when and why the SPO framework offers a superior decision to optimize vessel selection.

Method PPC for Precise Piecewise Correlation after Histogram Segmentation

Correlation, functioning as a symmetric relation, is very powerful indicator of the mutual association between two attributes. The problem of weak correlation indicates a lack of linearity in the observed range. This paper presents the precise piecewise correlation method, which overcomes the problem by determining the segments where the linear association will be present. The determination was achieved using the histogram segmentation method. The conditions of the application and analysis of the method are presented, as well as the application of the method to the representative datasets. The obtained results confirm the existence of stronger linear associations on the segments. Detected correlations reveal the strength and nature of the symmetric association between two attributes on each of the separated segments.

Bimodal Visualization of Industrial X-Ray and Neutron Computed Tomography Data.

Advanced manufacturing creates increasingly complex objects with material compositions that are often difficult to characterize by a single modality. Our collaborating domain scientists are going beyond traditional methods by employing both X-ray and neutron computed tomography to obtain complementary representations expected to better resolve material boundaries. However, the use of two modalities creates its own challenges for visualization, requiring either complex adjustments of bimodal transfer functions or the need for multiple views. Together with experts in nondestructive evaluation, we designed a novel interactive bimodal visualization approach to create a combined view of the co-registered X-ray and neutron acquisitions of industrial objects. Using an automatic topological segmentation of the bivariate histogram of X-ray and neutron values as a starting point, the system provides a simple yet effective interface to easily create, explore, and adjust a bimodal visualization. We propose a widget with simple brushing interactions that enables the user to quickly correct the segmented histogram results. Our semiautomated system enables domain experts to intuitively explore large bimodal datasets without the need for either advanced segmentation algorithms or knowledge of visualization techniques. We demonstrate our approach using synthetic examples, industrial phantom objects created to stress bimodal scanning techniques, and real-world objects, and we discuss expert feedback.

Dual-color space color correction and histogram segmentation optimized strategy for underwater image enhancement

Dual-color space color correction and histogram segmentation optimized strategy for underwater image enhancement

The problem of segmenting frequency histograms in the analysis of medical and biological data

Histogram segmentation is the task of identifying statistically significant peaks in a histogram corresponding to different types of objects. This could be identifying different cell types in cytometry (gating), finding objects in images, identifying different types of patients in gene expression data, analyzing a histogram of p-values in a multiple comparisons problem. A statistically motivated search for significant peaks requires the introduction of a null hypothesis describing a histogram in which there are no significant peaks. If a uniform distribution is accepted as the null hypothesis, then we considered the search for peaks and pits for frequency data, as well as clusters and voids in the primary data in previous publications. In practice, a more complex situation often arises when a unimodal distribution is considered as the null hypothesis without specifying its functional form. The paper proposes an approach to the problem of histogram segmentation, when structureless data is described by a unimodal distribution that best matches the original one. In addition, a comparison of two histograms is considered, which allows identifying local regions of divergence, thereby complementing the global chi-square test. The method can be used in bioinformatics, cytometry, and computer image analysis. As an example of a histogram segmentation problem, we consider Katz’s classical data on proving the discreteness of transmitter release into the synaptic gap.

Defect Isolation from Whole to Local Field Separation in Complex Interferometry Fringe Patterns through Development of Weighted Least-Squares Algorithm

In this paper, based on Gaussian 1σ-criterion and histogram segmentation, a weighted least-squares algorithm is applied and validated on digital holographic speckle pattern interferometric data to perform phase separation on the complex interference fields. The direct structural diagnosis tool is used to investigate defects and their impact on a complex antique wall painting of Giotto. The interferometry data is acquired with a portable off-axis interferometer set-up with a phase-shifted reference beam coupled with the object beam in front of the digital photosensitive medium. A digital holographic speckle pattern interferometry (DHSPI) system is used to register digital recordings of interferogram sequences over time. The surface is monitored for as long as it deforms prior to returning to its initial reference equilibrium state prior to excitation. The attempt to separate the whole vs. local defect complex amplitudes from the interferometric data is presented. The main aim is to achieve isolation and visualization of each defect’s impact amplitude in order to obtain detailed documentation of each defect and its structural impact on the surface for structural diagnosis purposes.

Dual Histogram Equalization Algorithm Based on Adaptive Image Correction

For the visual measurement of moving arm holes in complex working conditions, a histogram equalization algorithm can be used to improve image contrast. To lessen the problems of image brightness shift, image over-enhancement, and gray-level merging that occur with the traditional histogram equalization algorithm, a dual histogram equalization algorithm based on adaptive image correction (AICHE) is proposed. To prevent luminance shifts from occurring during image equalization, the AICHE algorithm protects the average luminance of the input image by improving upon the Otsu algorithm, enabling it to split the histogram. Then, the AICHE algorithm uses the local grayscale correction algorithm to correct the grayscale to prevent the image over-enhancement and gray-level merging problems that arise with the traditional algorithm. It is experimentally verified that the AICHE algorithm can significantly improve the histogram segmentation effect and enhance the contrast and detail information while protecting the average brightness of the input image, and thus the image quality is significantly increased.

A novel comparison of image semantic segmentation techniques for detecting dust in photovoltaic panels using machine learning and deep learning

The reduction in photovoltaic (PV) panel efficiency is a significant concern, especially for the photovoltaic power stations (PPS) near different soil types and a high wind presence. A relevant interest has emerged in developing systems capable of recognizing and evaluating the state of PV panels without human intervention. This work analyzes three different approaches to address this problem using semantic segmentation. The first approach employs unsupervised learning, while the second utilizes supervised learning, applying Machine Learning techniques such as K-means, Gaussian Mixture Models, Random Forest, and Light GBM, as well as more rudimentary options like histogram segmentation and color spaces. The final approach utilizes Deep Learning models, testing different versions of the U-net architecture primarily designed for image segmentation tasks. The results showcase the model's performance in terms of accuracy, processing and training time, F1 Score, and Intersection over Union. It was observed that supervised models with Machine Learning algorithms achieved a perfect balance between performance and speed. On the other hand, the Deep Learning approach proved more effective when the input was not standardized and the image format was poorly defined.

Automatic elimination of phase aberrations in digital holography based on Gaussian 1σ- criterion and histogram segmentation.

We propose a numerical and automatic quadratic phase aberration elimination method in digital holography for phase-contrast imaging. A histogram segmentation method based on Gaussian 1σ-criterion is used to obtain the accurate coefficients of quadratic aberrations using the weighted least-squares algorithm. This method needs no manual intervention for specimen-free zone or prior parameters of optical components. We also propose a maximum-minimum-average-standard deviation (MMASD) metric to quantitatively evaluate the effectiveness of quadratic aberration elimination. Simulation and experimental results are demonstrated to verify the efficacy of our proposed method over the traditional least-squares algorithm.

Automatic Segmentation of Periapical Radiograph Using Color Histogram and Machine Learning for Osteoporosis Detection.

Osteoporosis leads to the loss of cortical thickness, a decrease in bone mineral density (BMD), deterioration in the size of trabeculae, and an increased risk of fractures. Changes in trabecular bone due to osteoporosis can be observed on periapical radiographs, which are widely used in dental practice. This study proposes an automatic trabecular bone segmentation method for detecting osteoporosis using a color histogram and machine learning (ML), based on 120 regions of interest (ROI) on periapical radiographs, and divided into 60 training and 42 testing datasets. The diagnosis of osteoporosis is based on BMD as evaluated by dual X-ray absorptiometry. The proposed method comprises five stages: the obtaining of ROI images, conversion to grayscale, color histogram segmentation, extraction of pixel distribution, and performance evaluation of the ML classifier. For trabecular bone segmentation, we compare K-means and Fuzzy C-means. The distribution of pixels obtained from the K-means and Fuzzy C-means segmentation was used to detect osteoporosis using three ML methods: decision tree, naive Bayes, and multilayer perceptron. The testing dataset was used to obtain the results in this study. Based on the performance evaluation of the K-means and Fuzzy C-means segmentation methods combined with 3 ML, the osteoporosis detection method with the best diagnostic performance was K-means segmentation combined with a multilayer perceptron classifier, with accuracy, specificity, and sensitivity of 90.48%, 90.90%, and 90.00%, respectively. The high accuracy of this study indicates that the proposed method provides a significant contribution to the detection of osteoporosis in the field of medical and dental image analysis.

Cancer Regions in Mammogram Images Using ANFIS Classifier Based Probability Histogram Segmentation Algorithm

Every year, the number of women affected by breast tumors is increasing worldwide. Hence, detecting and segmenting the cancer regions in mammogram images is important to prevent death in women patients due to breast cancer. The conventional methods obtained low sensitivity and specificity with cancer region segmentation accuracy. The high-resolution standard mammogram images were supported by conventional methods as one of the main drawbacks. The conventional methods mostly segmented the cancer regions in mammogram images concerning their exterior pixel boundaries. These drawbacks are resolved by the proposed cancer region detection methods stated in this paper. The mammogram images are classified into normal, benign, and malignant types using the Adaptive Neuro-Fuzzy Inference System (ANFIS) approach in this paper. This mammogram classification process consists of a noise filtering module, spatial-frequency transformation module, feature computation module, and classification module. The Gaussian Filtering Algorithm (GFA) is used as the pixel smooth filtering method and the Ridgelet transform is used as the spatial-frequency transformation module. The statistical Ridgelet feature metrics are computed from the transformed coefficients and these values are classified by the ANFIS technique in this paper. Finally, Probability Histogram Segmentation Algorithm (PHSA) is proposed in this work to compute and segment the tumor pixels in the abnormal mammogram images. This proposed breast cancer detection approach is evaluated on the mammogram images in MIAS and DDSM datasets. From the extensive analysis of the proposed tumor detection methods stated in this work with other works, the proposed work significantly achieves a higher performance. The methodologies proposed in this paper can be used in breast cancer detection hospitals to assist the breast surgeon to detect and segment the cancer regions.

An Effective Method for Gas-Leak Area Detection and Gas Identification with Mid-Infrared Image

Mid-infrared imaging systems are widely applied in gas-leak detection. However, infrared images generally suffer from low contrast and poor quality. In this paper, an image-enhancement method based on Gaussian filtering and adaptive histogram segmentation is proposed to effectively improve the quality of infrared images. It can effectively improve the quality of infrared images, which contributes to the subsequent gas-image feature extraction. The traditional background modeling algorithm is analyzed, and the ViBe (visual background extractor) algorithm is studied in depth. Based on the advantages and disadvantages of the ViBe algorithm and the characteristics of gas-leak images, a gas-leak region detection method based on the improved ViBe algorithm is proposed. The test results show that it can quickly establish a background model, segment the gas-leak region with motion characteristics, and render the gas-leak region in color based on grayscale mapping to achieve the automatic detection and enhanced display of gas leaks.

An automatic and intelligent brain tumor detection using Lee sigma filtered histogram segmentation model.

Brain tumors are the second important origin of death worldwide. The early and exact identification of brain tumors is significant for the healing process. With accelerating diagnoses, medicine as well as pricing, quantum computing permits disruptive cases to providers. Quantum improved deep learning was especially significant to the sector. However, the conventional machine learning method faces main challenges to achieve accurate brain tumor detection with MRI images. Therefore, this paper proposes a novel technique called Lee sigma filtered histogram segmentation (LSFHS) for accurately detecting brain tumors with minimal time consumption. LSFHS technique is based on preprocessing, segmentation, feature extraction and classification. Input MRI image is preprocessed using adaptive Lee sigma filter in the first hidden layer to minimize noise significantly. In hidden layer 2, gray bimodal histogram segmentation is performed to partition a preprocessed image into a number of segments. Multiple features are extracted from the input image in the third hidden layer. Output layer uses the TanH activation function to match extracted features with disease features for detecting brain tumors. Experimental evaluation is carried out on factors, namely peak signal-to-noise ratio, tumor detection accuracy, error rate and tumor detection with a number of MRI images. The results illustrate LSFHS technique increases tumor detection accuracy by 14% and 25% faster tumor detection time, and reduces the error rate by 58% compared to state-of-the-art works. Qualitative and quantitative results illustrate that our proposed LSFHS technique attains greater performance than state-of-the-art methods. LSFHS technique is designed to detect brain tumors at an earlier stage with higher tumor detection accuracy and less time.

U-Net architecture variants for brain tumor segmentation of histogram corrected images

Abstract In this paper we propose to create an end-to-end brain tumor segmentation system that applies three variants of the well-known U-Net convolutional neural networks. In our results we obtain and analyse the detection performances of U-Net, VGG16-UNet and ResNet-UNet on the BraTS2020 training dataset. Further, we inspect the behavior of the ensemble model obtained as the weighted response of the three CNN models. We introduce essential preprocessing and post-processing steps so as to improve the detection performances. The original images were corrected and the different intensity ranges were transformed into the 8-bit grayscale domain to uniformize the tissue intensities, while preserving the original histogram shapes. For post-processing we apply region connectedness onto the whole tumor and conversion of background pixels into necrosis inside the whole tumor. As a result, we present the Dice scores of our system obtained for WT (whole tumor), TC (tumor core) and ET (enhanced tumor) on the BraTS2020 training dataset.

Determination of dynamics and stage of development of COVID-19 pneumonia based on digital software processing of images of computed tomography of the chest

BACKGROUND. Pneumonia resulting from SARS-CoV-2 infection is characterized by the development of certain radiological patterns such as “ground glass” and others, which can only be detected using high-resolution computed tomography (HRCT) of the chest. The use of CT to combat the coronavirus disease (COVID-19) pandemic varies worldwide. In scientific publications, there is no consensus on the information content of CT for COVID-19 pneumonia, the timing of its implementation at the onset of the disease and control examinations. The long-term consequences of the disease, the possibilities of software processing of CT images of the chest cavity in order to study the dynamics of the process, predict outcomes and evaluate the effectiveness of the therapy, have not been sufficiently studied.
 OBJECTIVE. To determine the possibilities of digital software processing to increase the information content of CT images and justify its use in determining the dynamics and stage of development of COVID-19 pneumonia.
 MATERIALS AND METHODS. For image analysis, we used the Dragonfly program, which was provided free of charge for non-commercial scientific research by Object Research Systems (Montreal, Canada). The program allows you to carry out segmentation, mathematical and statistical processing of images, to build conventional and segmented histograms. To use it, it is necessary to reformat DICOM files of CT into so-called raster files (TIFF, JPEG). Further analysis of images of CT slices is performed using gray scale (from 64 to 512 gradations), which correlates with density values on the Hounsfield scale, which allows you to more accurately determine the structure of the organ under study.
 RESULTS AND DISCUSSION. The analysis of CT for COVID-19 pneumonia with the “ground glass” pattern showed that standard densitometry does not allow to determine the morphofunctional difference between the studied areas of “ground glass” and to determine the stage of its development. The segmentation histogram based on digital software processing of the same “ground glass” areas of the patient with COVID-19 pneumonia has changed significantly with a clear definition of a significant difference in the density of the pattern in dynamics, on the basis of which it can be concluded that the patient is undergoing a process of recovery and COVID-19 pneumonia is at the resolution stage.
 CONCLUSIONS. Carrying out digital software image processing with a CT segmentation histogram allows you to determine the dynamics and stage of development of COVID-19 pneumonia, evaluate the effectiveness and need for therapeutic measures. In order to conduct an objective control of the inflammatory process in COVID-19 pneumonia, it is necessary to conduct a HRCT of the chest at discharge from the hospital, especially in patients who were treated in the intensive care unit. If there are significant changes, follow-up studies should be carried out after 3 and 6 months, or depending on clinical indications.

Traditional Pattern Feature Extraction and Cultural Creative Design Application Based on Multilevel Histogram Shape Segmentation

Content-based stereo video and image retrieval relies on traditional pattern feature extraction and cultural creative design applications. In a 3D system, the 3D model is typically projected into a 2D point cloud, after which feature extraction takes place. A depth map is an image created by orthogonal projection of three-dimensional data or viewpoint matching, parallax calculation, and resampling into regular data based on depth value. In this paper, a multilevel histogram-based shape segmentation method is proposed. The threshold can be determined by analyzing the relationship between the peaks if there are several obvious peaks on the image histogram. This paper focuses on the use of traditional pattern feature extraction and cultural creative design based on the shape segmentation of multilevel histograms. Each algorithm can achieve good classification results in the experiment of rotation invariant similarity classification. The average accuracy of the HOD algorithm is 84.1%, the average accuracy of the RSDF algorithm is 86.2%, the average accuracy of the GIF algorithm is 81.3%, and the average accuracy of this paper’s algorithm is 89.9% when the rotation angle is 60–120°. The results show that this paper’s algorithm has a higher classification accuracy compared to the other algorithms and that it maintains a high average classification accuracy across all rotation angles, indicating that it is rotation invariant and robust. The histogram-based threshold method has the advantage of not requiring knowledge of the image’s prior information. The algorithm is easy to understand, straightforward, and quick. However, because the valley point in the histogram is not visible in images with low or high contrast between the target and the background area, it is difficult to select the threshold. The results of traditional pattern feature extraction can be improved using the retrieved pixels.

The Cuts Selection Method Based on Histogram Segmentation and Impact on Discretization Algorithms.

The preprocessing of data is an important task in rough set theory as well as in Entropy. The discretization of data as part of the preprocessing of data is a very influential process. Is there a connection between the segmentation of the data histogram and data discretization? The authors propose a novel data segmentation technique based on a histogram with regard to the quality of a data discretization. The significance of a cut’s position has been researched on several groups of histograms. A data set reduct was observed with respect to the histogram type. Connections between the data histograms and cuts, reduct and the classification rules have been researched. The result is that the reduct attributes have a more irregular histogram than attributes out of the reduct. The following discretization algorithms were used: the entropy algorithm and the Maximal Discernibility algorithm developed in rough set theory. This article presents the Cuts Selection Method based on histogram segmentation, reduct of data and MD algorithm of discretization. An application on the selected database shows that the benefits of a selection of cuts relies on histogram segmentation. The results of the classification were compared with the results of the Naïve Bayes algorithm.

Image Enhancement Algorithm of Electrowetting Display Based on Image Segmentation and Dynamic Histogram Equalization

Image Enhancement Algorithm of Electrowetting Display Based on Image Segmentation and Dynamic Histogram Equalization

Selective Hole Filling of Red Blood Cells for Improved Marker-Controlled Watershed Segmentation.

Manual counting and evaluation of red blood cells with the presence of malaria parasites is a tiresome, time-consuming process that can be altered by environmental conditions and human error. Many algorithms were presented to segment red blood cells for subsequent parasitemia evaluation by machine learning algorithms. However, the segmentation of overlapping red blood cells always has been a challenge. Marker-controlled watershed segmentation is one of the methods that was implemented to separate overlapping red blood cells. However, a high number of overlapped red blood cells were still an issue. We propose a novel approach to improve the segmentation efficiency of marker-controlled watershed segmentation. Local minimum histogram background segmentation with a selective hole filling algorithm was introduced to improve segmentation efficiency of marker-controlled watershed segmentation on a high number of overlapping red blood cells. The local minimum was selected on the smoothed histogram for background segmentation. The combination of selective filling, convex hull, and Hough circle detection algorithms was utilized for the intact segmentation of red blood cells. The markers were computed from the resulted mask, and finally, marker-controlled watershed segmentation was applied to separate overlapping red blood cells. As a result, the proposed algorithm achieved higher background segmentation accuracy compared to popular background segmentation algorithms, and the inclusion of corner details improved watershed segmentation efficiency.

DAGDU: center location of tropical cyclones using Deviation Angle Gradient Distribution Uniformity from infrared satellite images

ABSTRACT The tropical cyclone (TC) is a strong weather system that forms on the surface of the ocean. It is important to locate the TC centre when monitoring and forecasting. Infrared geostationary satellite images are reliable sources of TC location due to their high temporal resolution and wide regional coverage. A novel method for locating the centre of tropical cyclones by deviation angle gradient distribution uniformity is proposed in this paper. A region of interest is first intercepted from an infrared image with a spatial resolution of 5 km per pixel derived from the China FY-2 C and FY-2E geostationary satellites. The Bezier histogram segmentation method and K-means clustering segmentation method are then used to obtain the binary image in which the infrared brightness temperature changes drastically. Next, Hough transformation is utilized to reduce the search range of the centre location of the tropical cyclone. Finally, the deviation angle gradient distribution uniformity matrix is calculated from each pixel in the detection area as the reference centre, and the maximum value location of the matrix is considered to be the corresponding tropical cyclone centre. The methodology of this study could achieve good performance compared with the best track data of the China Meteorological Administration (CMA), the Japan Meteorological Agency (JMA), and the United States Joint Typhoon Warning Center (JTWC).