Edge-based Segmentation Methods Research Articles

Performance Evaluation of Edge-Based Segmentation Methods for Electrical Tree Image Analysis in High-Voltage Experiments

Performance Evaluation of Edge-Based Segmentation Methods for Electrical Tree Image Analysis in High-Voltage Experiments

Microvascular imaging of the unstained human superior colliculus using synchrotron-radiation phase-contrast microtomography

Characterizing the microvasculature of the human brain is critical to advance understanding of brain vascular function. Most methods rely on tissue staining and microscopy in two-dimensions, which pose several challenges to visualize the three-dimensional structure of microvessels. In this study, we used an edge-based segmentation method to extract the 3D vasculature from synchrotron radiation phase-contrast microtomography (PC-μCT) of two unstained, paraffin-embedded midbrain region of the human brain stem. Vascular structures identified in PC-μCT were validated with histology of the same specimen. Using the Deriche-Canny edge detector that was sensitive to the boundary between tissue and vascular space, we could segment the vessels independent of signal variations in PC-μCT images. From the segmented volumetric vasculature, we calculated vessel diameter, vessel length and volume fraction of the vasculature in the superior colliculi. From high resolution images, we found the most frequent vessel diameter to be between 8.6–10.2 µm. Our findings are consistent with the known anatomy showing two types of vessels with distinctive morphology: peripheral collicular vessels and central collicular vessels. The proposed method opens up new possibilities for vascular research of the central nervous system using synchrotron radiation PC-μCT of unstained human tissue.

Image Segmentation Techniques for Intelligent Monitoring of Putonghua Examinations

Image recognition and image processing usually contain the technique of image segmentation. Excellent segmentation results can directly affect the accuracy of image recognition and processing. The essence of image segmentation is to segment each frame of a certain image or a video into multiple specific objects or regions and represent them with different labels. This paper focuses on the segmentation results obtained in image segmentation of images used for intelligent monitoring of Mandarin exams are usually visualized for image analysis. In this paper, we first investigate the performance improvement techniques for semantic segmentation in the image segmentation task for intelligent monitoring of Mandarin exams, improve the pixel classification capability by performing semantic migration, and, for the first time, extend the dataset substantially by style transformation to improve the model’s recognition of advanced features. In addition, to further address the shortcomings of the dataset, this paper improves the performance of image segmentation using synthetic datasets by investigating synthetic dataset image segmentation improvement techniques that reduce the reliance on manually annotated datasets. Image segmentation techniques continue to advance, and there are even thousands of commonly used segmentation methods for image segmentation development to date. Among them, they can be broadly classified as region-based segmentation methods, threshold-based segmentation methods, edge-based segmentation methods, specific theory-based segmentation methods, and deep learning-based segmentation methods. However, the methods used in this paper have all been experimentally demonstrated to improve the effectiveness of the techniques and proved to outperform other existing methods in the same field in the publicly available datasets LSUN, Cityscapes, and GTA5 datasets, respectively.

Review of Edge-based Image Segmentation on Electrical Tree Classification in Cross-linked Polyethylene (XLPE) Insulation

Electrical trees are the degradation events most linked with partial discharge (PD) activity in cross-linked polyethylene (XLPE) insulation of high voltage (HV) cables. To investigate tree structures and forms, study of electrical tree structures for morphological analysis often carried out using optical microscopy. However, since the noise induced by the occlusion and illumination, as well as by non-uniform intensity either from optical device’s setting or the non-standard readout procedure, causes the deterioration of the original microscopy images, resulting in critically loses of information pertaining the tree structures making it difficult to obtained accurate measurement. Image segmentation is one of the potential solutions as it is well-suited for extracting information or certain features from microscopy images. This paper provides review of several segmentation techniques applied on the classification of electrical tree image acquired through lab environment. The works can be separated into three stages. The first step includes the preparation of samples and collection of treeing images by means of real-time microscopy observations. The captured data would then be pre-processed to achieve image binarization. In the next step, image segmentation process is conducted using existing edge-based segmentation methods including Prewitt, Roberts, Canny and Kirsch’s templates. Later, comparative analysis will be performed using IQA (image quality assessment) metrics of accuracy, sensitivity, specificity, false-positive-rate and the Matthews Correlation Coefficient (MCC) as the final step. Performance-wise indicates that Kirsch’s template able to segment most of the treeing pixels with accuracy of 97.63%, 63% sensitivity, 98.18% specificity and 0.46 MCC while showing low pixels misclassification. This result provides better justification for the integration of the edge-based technique in developing image segmentation algorithm well-matched for the electrical tree analysis in the future.

Overview of the Whole Heart and Heart Chamber Segmentation Methods.

Preservation and improvement of heart and vessel health is the primary motivation behind cardiovascular disease (CVD) research. Development of advanced imaging techniques can improve our understanding of disease physiology and serve as a monitor for disease progression. Various image processing approaches have been proposed to extract parameters of cardiac shape and function from different cardiac imaging modalities with an overall intention of providing full cardiac analysis. Due to differences in image modalities, the selection of an appropriate segmentation algorithm may be a challenging task. This paper presents a comprehensive and critical overview of research on the whole heart, bi-ventricles and left atrium segmentation methods from computed tomography (CT), magnetic resonance (MRI) and echocardiography (echo) imaging. The paper aims to: (1) summarize the considerable challenges of cardiac image segmentation, (2) provide the comparison of the segmentation methods, (3) classify significant contributions in the field and (4) critically review approaches in terms of their performance and accuracy. The methods described are classified based on the used segmentation approach into (1) edge-based segmentation methods, (2) model-fitting segmentation methods and (3) machine and deep learning segmentation methods and are further split based on the targeted cardiac structure. Edge-based methods are mostly developed as semi-automatic and allow end-user interaction, which provides physicians with extra control over the final segmentation. Model-fitting methods are very robust and resistant to the high variability in image contrast and overall image quality. Nevertheless, they are often time-consuming and require appropriate models with prior knowledge. While the emerging deep learning segmentation approaches provide unprecedented performance in some specific scenarios and under the appropriate training, their performance highly depends on the data quality and the amount and the accuracy of provided annotations.

Object Detection In Underwater Acoustic Images Using Edge Based Segmentation Method

Abstract Image segmentation techniques play a vital role in partitioning the image into segments. These techniques are used for detecting the objects in the images. The real challenge in the acoustic image segmentation lies in differentiating the sea floor, sediments and the objects. Due to the typical characteristics and low resolution of the acoustic images, segmentation techniques such as region based, morphological based and edge based methods are not suitable. The sediments will also be traced along with the objects that makes the detection process a very difficult one. In this research paper, edge based segmentation method that uses the morphological operations for identifying the edges followed by a object tracing algorithm is proposed. The images used in this work are captured in real time using Edgetech 4125 Side scan sonar device. The acoustic images are first pre-processed using Wiener and Median filters and a morphological gradient is obtained by subtracting the morphologically dilated and eroded image. Next the edge map of the acoustic images are obtained using binarization method by which the object’s boundary is made visible. Finally a Moore’s object tracing algorithm is used for detecting the objects in the images.

Biomedical Image Segmentation using Optimized Fuzzy C-mean Algorithm

Background/Objectives: Automatic segmentation of brain MRI has an important role in image research along with medical image processing. It has been investigated widely in recent research. It helps for patient diagnosis for different diseases its value concerns in diagnostics through various biomedical images such as PET, CT, MRI and X-ray. In this paper, we analyzed for different biomedical images using partition method. The objective is to detect patch in the biomedical images that may lead to tumors. Methods/Statistical Analysis: The objective of segmentation is to divide the complete image into informative regions and respective specific application. Segmentation separates the image from the background, read the contents and isolating it. Both the concept of clustering by fuzzy technique with edge based segmentation method where standard methods like Sobel, Prewitt edge detectors are applied. Further it is optimized using evolutionary algorithm for efficient minimization of the objective function to improve classification accuracy. Findings: To find the smooth image Gaussian filter is used. Successive segmentation has been performed to detect the patch of desired region. It is observed for different images and compared. Improvements/Applications: It will be helpful for clinical analysis and observe the quality of images for diagnosis of diseases. Keywords: Clustering, Fuzzy C-mean Algorithm, Genetic Algorithm, Optimization, PSO, Thresholding

Automated bare earth extraction technique for complex topography in light detection and ranging surveys

Bare earth extraction is an important component to light detection and ranging (LiDAR) data analysis in terms of terrain classification. The challenge in providing accurate digital surface models is augmented when there is diverse topography within the data set or complex combinations of vegetation and built structures. Few existing algorithms can handle substantial terrain diversity without significant editing or user interaction. This effort presents a newly developed methodology that provides a flexible, adaptable tool capable of integrating multiple LiDAR data attributes for an accurate terrain assessment. The terrain extraction and segmentation (TEXAS) approach uses a third-order spatial derivative for each point in the digital surface model to determine the curvature of the terrain rather than rely solely on the slope. The utilization of the curvature has shown to successfully preserve ground points in areas of steep terrain as they typically exhibit low curvature. Within the framework of TEXAS, the contiguous sets of points with low curvatures are grouped into regions using an edge-based segmentation method. The process does not require any user inputs and is completely data driven. This technique was tested on a variety of existing LiDAR surveys, each with varying levels of topographic complexity.

Image Segmentation Based on Poisson Equation

Image segmentation is an important part of the image processing. Currently, image segmentation methods are mainly the threshold-based segmentation method, the region-based segmentation method, the edge-based segmentation method and the Snake model based on energy function etc. This paper presents a novel image segmentation method based on the Poisson equation. The goal of the segmentation method is to divide the image into two homogeneous parts, the boundary portion and the non-boundary portion, which have similar gray values in homogeneous part. The key of the method is to build a Poisson equation with Dirichlet boundary condition. It sets a gradient threshold as the Dirichlet boundary condition of the Poisson equation, and gets a binary image by retaining the image boundary and smoothing the non-image boundary. Then simple binary segmentation will be able to get the image boundary. The experimental results show that this segmentation method can get accurate image boundaries for non-noise images and the weak noise images.

An Experimental Study and Analysis of Different Image Segmentation Techniques

Image segmentation is a process of classifying or identifying sub patterns in a given image. Image segmentation is widely used in applications like automatic pattern recognition, content based image retrieval, machine vision, medical imaging, face detection and object detection. In this work, different image segmentation methods like threshold based, region based segmentation and edge based segmentation methods are explored. Experiments have been done using MATLAB 7.12 and the standard benchmark images from Berkeley database are used. Different edge detection methods such as Sobel, Prewitt and Canny methods are performed on the benchmark images and the performance is analyzed with respect to accuracy and error rate. Simple, multiple threshold and region based methods are also tested on the benchmark images. Texture filters such as range, entropy and standard deviation are experimented on the texture images.

Hybrid JPEG Compression Using Edge Based Segmentation

A hybrid image compression method is proposed in this paper which segments the image into background and foreground and compress them with different quality levels.. The foreground of the image is given more importance than the background. An edge based segmentation method is used to segment the image into foreground area and background area. The proposed method highly preserves quality of the foreground image. JPEG compression is a widely used compression technique. Normally the JPEG compression method uses linear quantization and threshold values to maintain certain quality level in an entire image. The proposed method adapts variable quantization and threshold values corresponding to background and foreground. This ensures that the vital area of the image is highly preserved than the other areas of the image. This hybrid approach increases the compression ratio and produces a desired high quality compressed image.

INTEGRATING EDGE DETECTION AND THRESHOLDING APPROACHES TO SEGMENTING FEMORA AND PATELLAE FROM MAGNETIC RESONANCE IMAGES

Anterior knee pain (AKP) is a common pathological condition. The most obvious problem causing knee pain is the abnormal patellar tracking mechanism. For computerized knee joint analysis, how to successfully segment the knee bones is an import issue. This paper presents a simple while effective algorithm for fully automatic femur and patella segmentation for magnetic resonance (MR) knee images through integrating edge detection and thresholding approaches. Based on consideration of computational complexity and accuracy, we develop a compound approach to segment the MR knee images. The moment preserving thresholding is first utilized to gather the bone-outline information employed to estimate the region of interest (ROI). An ROI based wavelet enhancement is proposed to restrict the contrast improvement only around the bone edges. The restriction makes both the adhesion separation of bone and surrounding tissues and the bone contour conservation become possible and avoid harsh thresholding resulting from the global based wavelet enhancement. Cooperating with the morphology operation, stable initial guess of the bone regions can be achieved. To overwhelm the main drawback of the existing edge based segmentation methods, i.e. the necessity of complicated post-processing, a new approach - FLoG is proposed to provide a feasible solution. It converts the edge detection results using LoG into a region-based format through the flow fill operation. The developed onion-growing algorithm can properly combine the initial guess of bone regions with the FLoG outputs in an efficient way. The experimental study shows our method is superior to the conventional ones in meeting the requirement of physicians. This is because our method can perform well in dealing with the tougher conditions, i.e. the partial volume and the soft tissue adhesion conditions. Because of the integration of the thresholding approach with the FLoG edge detector, our algorithm is even robust to unsatisfactory imaging conditions. Hence, our method lends itself to assisting the clinical diagnosis of knee functions.

Inspecting pizza topping percentage and distribution by a computer vision method

Topping percentage and distribution are two major features in the quality inspection of pizzas. The extraction of these features highly depends on the segmentation quality of pizza images. However, complex visual features and wide varieties of pizzas make the segmentation task difficult. Traditional segmentation methods are found only partly suitable for most pizza images. Therefore, a new segmentation method was developed by using the region-based segmentation as a dominant method and combining the strengths of both thresholding and edge-based segmentation methods. For evaluating the evenness of topping distribution, a practical method of dividing a pizza image into several equal-area partitions was developed. The experimental results show that the computer vision method developed is suitable for many different types of pizzas with an accuracy of over 90% for measuring topping exposure percentage and distribution.

Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples.

This paper provides methodology for fully automated model-based image segmentation. All information necessary to perform image segmentation is automatically derived from a training set that is presented in a form of segmentation examples. The training set is used to construct two models representing the objects--shape model and border appearance model. A two-step approach to image segmentation is reported. In the first step, an approximate location of the object of interest is determined. In the second step, accurate border segmentation is performed. The shape-variant Hough transform method was developed that provides robust object localization automatically. It finds objects of arbitrary shape, rotation, or scaling and can handle object variability. The border appearance model was developed to automatically design cost functions that can be used in the segmentation criteria of edge-based segmentation methods. Our method was tested in five different segmentation tasks that included 489 objects to be segmented. The final segmentation was compared to manually defined borders with good results [rms errors in pixels: 1.2 (cerebellum), 1.1 (corpus callosum), 1.5 (vertebrae), 1.4 (epicardial), and 1.6 (endocardial) borders]. Two major problems of the state-of-the-art edge-based image segmentation algorithms were addressed: strong dependency on a close-to-target initialization, and necessity for manual redesign of segmentation criteria whenever new segmentation problem is encountered.

Multiscale Segmentation of Three-Dimensional MR Brain Images

Segmentation of MR brain images using intensity values is severely limited owing to field inhomogeneities, susceptibility artifacts and partial volume effects. Edge based segmentation methods suffer from spurious edges and gaps in boundaries. A multiscale method to MRI brain segmentation is presented which uses both edge and intensity information. First a multiscale representation of an image is created, which can be made edge dependent to favor intra-tissue diffusion over inter-tissue diffusion. Subsequently a multiscale linking model (the hyperstack) is used to group voxels into a number of objects based on intensity. It is shown that both an improvement in accuracy and a reduction in image post-processing can be achieved if edge dependent diffusion is used instead of linear diffusion. The combination of edge dependent diffusion and intensity based linking facilitates segmentation of grey matter, white matter and cerebrospinal fluid with minimal user interaction. To segment the total brain (white matter plus grey matter) morphological operations are applied to remove small bridges between the brain and cranium. If the total brain is segmented, grey matter, white matter and cerebrospinal fluid can be segmented by joining a small number of segments. Using a supervised segmentation technique and MRI simulations of a brain phantom for validation it is shown that the errors are in the order of or smaller than reported in literature.

Edge‐based segmentation of range images: integrating roof and step edges

We investigate edge extraction and the segmentation of range images. We first discuss problems that arise in conventional region-based and edge-based segmentation methods, then we propose a new edge-based segmentation algorithm. In the proposed algorithm, we extract edge contours by using the Gaussian filter and directional derivatives and segment a range image by integrating detected roof and step edges. Thus the correspondence between step and roof edges is not necessary. Computer simulations with several range images show that the proposed edge-based range image segmentation method is simpler and yields better performance than the conventional methods.