Image Segmentation Results Research Articles

Tongue image segmentation via color decomposition and thresholding

SummaryTongue image segmentation is a crucial step in developing an automatic tongue diagnosis system. After exploring characteristics of image thresholding in different color spaces, we propose a simple and effective tongue image segmentation method. Specifically, the proposed method first extracts an initial tongue body region by performing image thresholding on the transformed hue component in HSI (Hue, Saturation, and Intensity) color space. Then, one of two image thresholding results on the red component of an original tongue image is adaptively selected to find the gap region between the tongue body root and the upper lip. Finally, the initial tongue body region is refined by removing fake object regions such as the upper lip to obtain final tongue image segmentation result. Experimental results on a tongue image dataset containing 200 subjects demonstrate the effectiveness of the proposed method.

Intraretinal layer segmentation and parameter measurement in optic nerve head region through energy function of spatial-gradient continuity constraint

For the diagnosis of glaucoma, optical coherence tomography (OCT) is a noninvasive imaging technique for the assessment of retinal layers. To accurately segment intraretinal layers in an optic nerve head (ONH) region, we proposed an automatic method for the segmentation of three intraretinal layers in eye OCT scans centered on ONH. The internal limiting membrane, inner segment and outer segment, Bruch’s membrane surfaces under vascular shadows, and interaction of multiple high-reflectivity regions in the OCT image can be accurately segmented through this method. Then, we constructed a novel spatial-gradient continuity constraint, termed spatial-gradient continuity constraint, for the correction of discontinuity between adjacent image segmentation results. In our experiment, we randomly selected 20 B-scans, each annotated three retinal layers by experts. Signed distance errors of −0.80 μm obtained through this method are lower than those obtained through the state-of-art method (−1.43 μm). Meanwhile, the segmentation results can be used as bases for the diagnosis of glaucoma.

Fast Bi-dimensional empirical mode decomposition as an image enhancement technique for fruit defect detection

Image enhancement is critical to detection of fruit defects by imaging techniques. Vignetting and noise are major image artifacts, which can seriously affect image segmentation results, especially in inspecting the curved-surface objects like fruit. It is common to use a calibration object or a mathematic model to reduce the vignetting effect in defect detection, but the approach is often cumbersome, inflexible, and difficult to achieve desired results. In this study, a new image enhancement method based on bi-dimensional empirical mode decomposition (BEMD) of images was proposed to isolate and subsequently remove the effects of vignetting and noise by means of selective image reconstruction. The new BEMD method, along with three other BEMD methods, was first tested on decomposing a synthetic image with artificially added vignetting and noise. The BEMD was found to be the most efficient for image decomposition in terms of computation time, and also give high-quality reconstructed images. Experiments were further conducted by applying the BEMD to the direct and amplitude component images of apple samples with subsurface bruising and surface defects, which were acquired by using a structured-illumination reflectance imaging (SIRI) system. BEMD effectively reduced the image vignetting and greatly enhanced the defect features of the apples, based on both visual inspection and quantitative evaluation. BEMD offers an effective tool for enhancing SIRI images, and it is also promising for image enhancement with other imaging modalities for fruit defect detection.

Apple Image Recognition Multi-Objective Method Based on the Adaptive Harmony Search Algorithm with Simulation and Creation

Aiming at the low recognition effect of apple images captured in a natural scene, and the problem that the OTSU algorithm has a single threshold, lack of adaptability, easily caused noise interference, and over-segmentation, an apple image recognition multi-objective method based on the adaptive harmony search algorithm with simulation and creation is proposed in this paper. The new adaptive harmony search algorithm with simulation and creation expands the search space to maintain the diversity of the solution and accelerates the convergence of the algorithm. In the search process, the harmony tone simulation operator is used to make each harmony tone evolve towards the optimal harmony individual direction to ensure the global search ability of the algorithm. Despite no improvement in the evolution, the harmony tone creation operator is used to make each harmony tone to stay away from the current optimal harmony individual for extending the search space to maintain the diversity of solutions. The adaptive factor of the harmony tone was used to restrain random searching of the two operators to accelerate the convergence ability of the algorithm. The multi-objective optimization recognition method transforms the apple image recognition problem collected in the natural scene into a multi-objective optimization problem, and uses the new adaptive harmony search algorithm with simulation and creation as the image threshold search strategy. The maximum class variance and maximum entropy are chosen as the objective functions of the multi-objective optimization problem. Compared with HS, HIS, GHS, and SGHS algorithms, the experimental results showed that the improved algorithm has higher a convergence speed and accuracy, and maintains optimal performance in high-dimensional, large-scale harmony memory. The proposed multi-objective optimization recognition method obtains a set of non-dominated threshold solution sets, which is more flexible than the OTSU algorithm in the opportunity of threshold selection. The selected threshold has better adaptive characteristics and has good image segmentation results.

Road Region Extraction from RSI using K-Mean HFT Segmentation Technique

The extraction of roads from digital images is essential for automatic mapping, effective urban planning and updating of GIS databases. The very high spatial resolution images (VHR) taken by space and space probes are the main source of an accurate extraction of the route. The extraction of road networks in remote urban areas of images plays an important role in many urban applications (eg. Road traffic, geometric correction of remote sensing images in cities, updating geographical information, etc.). Because of the complex geometry of buildings and the geometry of sensor detection, it is generally difficult to distinguish the road from its background. In this research work the image segmentation techniques used for image remote sensing are discussed and evaluated. It has been found that there is no perfect method for image segmentation because the result of image segmentation depends on many factors, i.e. Pixel color, consistency, intensity, image similarity, image content and problem area. In this research work, a hybrid method is proposed for the extraction of paths from high resolution images based on the segmentation of the mean and HFT segmentation. The proposed method includes: noise suppression using the Lucy-Richardson algorithm, then a further improvement of the contrast between the initial segmentation of road and non-road pixels using the segmentation means k and finally HFT based segmentation. Simulation will be conducted on remote sensing images in urban, suburban and rural areas to demonstrate the proposed method and compare it with other similar approaches. The results show the validity and superior performance of the proposed extraction method.

Weakly Supervised Biomedical Image Segmentation by Reiterative Learning.

Recent advances in deep learning have produced encouraging results for biomedical image segmentation; however, outcomes rely heavily on comprehensive annotation. In this paper, we propose a neural network architecture and a new algorithm, known as overlapped region forecast, for the automatic segmentation of gastric cancer images. To the best of our knowledge, this report for the first time describes that deep learning has been applied to the segmentation of gastric cancer images. Moreover, a reiterative learning framework that achieves superior performance without pretraining or further manual annotation is presented to train a simple network on weakly annotated biomedical images. We customize the loss function to make the model converge faster while avoiding becoming trapped in local minima. Patch boundary errors were eliminated by our overlapped region forecast algorithm. By studying the characteristics of the model trained using two different patch extraction methods, we train iteratively and integrate predictions and weak annotations to improve the quality of the training data. Using these methods, a mean Intersection over Union coefficient of 0.883 and a mean accuracy of 91.09% were achieved on the partially labeled dataset, thereby securing a win in the 2017 China Big Data and Artificial Intelligence Innovation and Entrepreneurship Competition.

Software for roof defects recognition on aerial photographs

The article presents information on software for roof defects recognition on aerial photographs, made with air drones. An areal image segmentation mechanism is described. It allows detecting roof defects – unsmoothness that causes water stagnation after rain. It is shown that HSV-transformation approach allows quick detection of stagnation areas, their size and perimeters, but is sensitive to shadows and changes of the roofing-types. Deep Fully Convolutional Network software solution eliminates this drawback. The tested data set consists of the roofing photos with defects and binary masks for them. FCN approach gave acceptable results of image segmentation in Dice metric average value. This software can be used in inspection automation of roof conditions in the production sector and housing and utilities infrastructure.

An active contour model for brain magnetic resonance image segmentation based on multiple descriptors

With the increasing use of surgical robots, robust and accurate segmentation techniques for brain tissue in the brain magnetic resonance image are needed to be embedded in the robot vision module. However, the brain magnetic resonance image segmentation results are often unsatisfactory because of noise and intensity inhomogeneity. To obtain accurate segmentation of brain tissue, one new multiphase active contour model, which is based on multiple descriptors mean, variance, and the local entropy, is proposed in this study. The model can bring about a more full description of local intensity distribution. Also, the entropy is introduced to improve the performance of robustness to noise of the algorithm. The segmentation and bias correction for brain magnetic resonance image can be simultaneously incorporated by introducing the bias factor in the proposed approach. At last, three experiments are carried out to test the performance of the method. The results in the experiments show that method proposed in this study performed better than most current methods in regard to accuracy and robustness. In addition, the bias-corrected images obtained by proposed method have better visual effect.

A Review on Segmentation Techniques in Large-Scale Remote Sensing Images

Information extraction is a very challenging task because remote sensing images are very complicated and can be influenced by many factors. The information we can derive from a remote sensing image mostly depends on the image segmentation results. Image segmentation is an important processing step in most image, video and computer vision applications. Extensive research has been done in creating many different approaches and algorithms for image segmentation. Labeling different parts of the image has been a challenging aspect of image processing. Segmentation is considered as one of the main steps in image processing. It divides a digital image into multiple regions in order to analyze them. It is also used to distinguish different objects in the image. Several image segmentation techniques have been developed by the researchers in order to make images smooth and easy to evaluate. Various algorithms for automating the segmentation process have been proposed, tested and evaluated to find the most ideal algorithm to be used for different types of images. In this paper a review of basic image segmentation techniques of satellite images is presented.

Color sensors and their applications based on real-time color image segmentation for cyber physical systems

Color information plays an important role in the color image segmentation and real-time color sensor, which affects the result of video image segmentation and correct real-time temperature value. In this paper, a novel real-time color image segmentation method is proposed, which is based on color similarity in RGB color space. According to the color and luminance information in RGB color space, the dominant color is determined at first, and then color similarity can be calculated with the proposed calculation method of color component, which creates a color-class map. Next, the information of the corresponding color-class map is utilized to classify the pixels. Due to the characteristic that thermal inks feature color values that change in real time as the temperature changes, the segmentation results of thermal ink can be used as a real-time color sensor. Then, we also propose a method of color correction and light source compensation for the sake of potential inaccuracy of its measures. We discuss the proposed segmentation method application combining with color sensor (thermal ink) in real-time color image segmentation for Cyber physical system (CPS) by the application in fire detection and summarize a new method in identifying fire in a video based on these characteristics. The experiments showed that the proposed method in vision-based fire detection and identification in videos was effective; the results were accurate and can be used in real-time analysis.

Fast and Automatically Adjustable GRBF Kernel Based Fuzzy C‐Means for Cluster‐wise Coloured Feature Extraction and Segmentation of MR Images

Fuzzy C-means algorithm is a popular image segmentation algorithm and many researchers in the past have introduced several improved versions of it. However, they still lacked robustness for segmenting key regions of magnetic resonance (MR) human brain transversal images such as white matter, grey matter, and cerebro spinal fluid with an almost similar contouring of the edges. This study highlights a robust algorithm that is effective in four ways: (i) a distinct contrast between different regions of the human brain, (ii) reduce noise as a result of the contrast stretching procedure, (iii) efficient analysis using both grey scale segmented image and its colour segmented version, and (iv) striking a balance between time consumption and image segmentation results. These objectives have been achieved in two phases: first, MR image segmentation using fast and automatically adjustable Gaussian radial basis function kernel based fuzzy C-means (FAAGKFCM) algorithm which utilises a new objective function that incorporates a similarity measure having both spatial and grey level measure factor ( S ij ), an adaptive factor ( w i ) to remove discrepancy of grey scale image, and using a Gaussian radial basis function (GRBF) kernel-based distance metric in place of the traditional Euclidean distance metric. Second, converting FAAGKFCM segmented image into CIE L * a * b * colour space and successively performing cluster-wise feature extraction using hard k-means clustering.

Production prediction for fracture-vug carbonate reservoirs using electric imaging logging data

Abstract Considering the fluid flow non-darcy characteristics in fracture-vug carbonate reservoirs, a new multi-scale conduit flow model production prediction method for fracture-vug carbonate reservoirs was presented using image segmentation technique of electric imaging logging data. Firstly, based on Hagen-Poiseuille's law of incompressible fluid flow and the different cross-sectional areas in single fractures and vugs in carbonate reservoirs, a multi-scale conduit flow model for fracture-vug carbonate reservoir was established, and a multi-scale conduit radial fluid flow equation was deduced. Then, conduit flow production index was introduced. The conduit flow production index was calculated using fracture-vug area extracted from the result of electrical image segmentation. Finally, production prediction of fracture-vug carbonate reservoir was realized by using electric imaging logging data. The method has been applied to Ordovician fracture-vug carbonate reservoirs in the Tabei area, and the predicted results are in good agreement with the oil testing data.

Medical image segmentation methods overview

This article provides an overview of the modern medical image segmentation methods. The most popular methods such as multi-atlas based methods and deep learning approach are considered in more details. In addition, this article overviews different steps of the multi-atlas based methods (MAS) in detail and shows which modern algorithms and approaches used in different steps of MAS to achieve state of the art results in the medical image segmentation task and how it affects the accuracy of the algorithm. Also, there is a brief description of the modern deep learning algorithms which are used for the medical image segmentation. Such type of algorithm is used as an independent algorithm or as a part of the MAS. Finally, this article summarizes described algorithms and evaluate which approaches promise to improve state of the art result of the medical image segmentation in the future.

Study on Underwater Sea Cucumber Rapid Locating Based on Morphological Opening Reconstruction and Max-Entropy Threshold Algorithm

In China, sea cucumber cultivation is developing rapidly, but sea cucumber catching still relies on inefficient manual work. Nowadays, the acquisition of underwater sea cucumber images and locating of sea cucumber target have provided technical support for underwater sea cucumber catching robots. However, there are still some problems to be solved, such as the degradation, edge blur and low contrast of underwater sea cucumber images due to the uneven light underwater and the absorption and scattering of light by water; and the cusp noises in the sea cucumber images produced by shells, gravers, planktons and other things in natural environment. Aiming at these problems, the underwater sea cucumber rapid locating method based on morphological opening reconstruction and max-entropy threshold algorithm (OR-META) is proposed in this paper. Firstly, the morphological opening reconstruction is adopted to smooth the original sea cucumber gray image; next, the max-entropy threshold segmentation algorithm is employed to segment the smoothed sea cucumber image, and the sea cucumber region in binary image is recognized according to area characteristics; finally, the position of sea cucumber region in the image is determined utilizing its centroid. In order to obtain the best result of sea cucumber image segmentation, three typical image segmentation algorithms OR-2DMETA, OR-OTSU and OR-2DOTSU are selected to compare with the OR-META. It is observed that the OR-META is obviously superior to the other three algorithms in qualitatively analyzing the image segmentation quality and quantitatively calculating the running time. To further analyze the image segmentation quality and locating accuracy, the images segmented by the OR-META are compared with manually segmented images. The comparison shows that although the image segmentation accuracy of the OR-META is low, with average target segmentation correct rate of 68.99%, the position of sea cucumber target in segmentation is predictable, which means that it will be within the directly drawn sea cucumber region. This demonstrates that the locating accuracy of the method is high. In addition, the method also has good real-time performance. It can be concluded from the experiment that for a RGB image with resolution ratio of 1280[Formula: see text][Formula: see text][Formula: see text]720 pixels, the average centroid Euclidean distance error of the OR-META segmented image is only 52.67 pixels, and its average running time is 0.6 s, which are qualified for the requirements of the sea cucumber catching robots.

Meta-heuristic moth swarm algorithm for multilevel thresholding image segmentation

Multilevel thresholding is a very important image processing technique in the field of image segmentation. However, the computational complexity of determining the optimal threshold grows exponentially with increasing thresholds. To overcome this drawback, in this paper, we propose a multi-threshold image segmentation method based on the moth swarm algorithm. The meta-heuristic algorithm uses Kapur’s entropy method to optimize the thresholds for eight standard test images. When compared with other state-of-the-art evolutionary algorithms, the proposed method proved to be robust and effective according to numerical experimental results and image segmentation results. This indicates the high performance of the method for the segmentation of digital images.

Heterogeneous SPCNN and its application in image segmentation

Abstract Based on the fact that actual cerebral cortex has different structure, a new heterogeneous simplified pulse coupled neural network (HSPCNN) model is proposed in this paper for image segmentation. HSPCNN is constructed with several simplified pulse coupled neural network (SPCNN) models, which have different parameters corresponding to different neurons. An image is segmented by HSPCNN into several regions according to their gray levels. Moreover, the parameter of HSPCNN is set automatically in this paper, the experimental segmentation results of the gray natural images from the Berkeley Segmentation Dataset (BSD 300) show the validity and efficiency of the proposed segmentation method. Finally, an evaluation index is proposed to measure the segmentation result.

Optimal Segmentation of High-Resolution Remote Sensing Image by Combining Superpixels With the Minimum Spanning Tree

Image segmentation is the foundation of object-based image analysis, and many researchers have sought optimal segmentation results. The initial image oversegmentation and the optimal segmentation scale are two vital factors in high spatial resolution remote sensing image segmentation. With respect to these two issues, a novel image segmentation method combining superpixels with a minimum spanning tree is proposed in this paper. First, the image is oversegmented using a simple linear iterative clustering algorithm to obtain superpixels. Then, the superpixels are clustered by regionalization with a dynamically constrained agglomerative clustering and partitioning (REDCAP) algorithm using the initial number of segments, and the local variance (LV) and the rate of LV change (ROC-LV) indicator diagrams corresponding to the number of segments are obtained. The suitable number of image segments is determined according to the LV and ROC-LV indicator diagrams corresponding to the number of segments. Finally, the superpixels are reclustered using the REDCAP algorithm based on the suitable number of image segments to obtain the image segmentation result. Through two sets of experiments, the proposed method is compared with two other segmentation algorithms. The experimental results show that the proposed method outperforms the others and obtains good image segmentation results.

Robust Student's-t mixture modelling via Markov random field and its application in image segmentation

Finite mixture model has been widely applied to image segmentation. However, the technique does not consider the spatial information in images that leads to unsatisfactory results for image segmentation. To address this problem, in this paper, a Student's-t mixture model is proposed for image segmentation based on Markov random field (MRF). There are three advantages in the proposed model. Firstly, a representation of spatial relationships among pixels is given. Secondly, Student's t-distribution is chosen to be the component function of the proposed model instead of the Gaussian distribution because of its heavy tail. Thirdly, to deduce the parameters of the proposed model, a gradient descent method is applied during the inference process. Comprehensive experiments are carried out on greyscale noisy images and real-world colour images. The experimental results have shown the effectiveness and robustness of the proposed model.

Robust Student's-t mixture modelling via Markov random field and its application in image segmentation

Finite mixture model has been widely applied to image segmentation. However, the technique does not consider the spatial information in images that leads to unsatisfactory results for image segmentation. To address this problem, in this paper, a Student's-t mixture model is proposed for image segmentation based on Markov random field (MRF). There are three advantages in the proposed model. Firstly, a representation of spatial relationships among pixels is given. Secondly, Student's t-distribution is chosen to be the component function of the proposed model instead of the Gaussian distribution because of its heavy tail. Thirdly, to deduce the parameters of the proposed model, a gradient descent method is applied during the inference process. Comprehensive experiments are carried out on greyscale noisy images and real-world colour images. The experimental results have shown the effectiveness and robustness of the proposed model.

Automated choroid segmentation of three-dimensional SD-OCT images by incorporating EDI-OCT images

Background and ObjectiveThe measurement of choroidal volume is more related with eye diseases than choroidal thickness, because the choroidal volume can reflect the diseases comprehensively. The purpose is to automatically segment choroid for three-dimensional (3D) spectral domain optical coherence tomography (SD-OCT) images. MethodsWe present a novel choroid segmentation strategy for SD-OCT images by incorporating the enhanced depth imaging OCT (EDI-OCT) images. The down boundary of the choroid, namely choroid-sclera junction (CSJ), is almost invisible in SD-OCT images, while visible in EDI-OCT images. During the SD-OCT imaging, the EDI-OCT images can be generated for the same eye. Thus, we present an EDI-OCT-driven choroid segmentation method for SD-OCT images, where the choroid segmentation results of the EDI-OCT images are used to estimate the average choroidal thickness and to improve the construction of the CSJ feature space of the SD-OCT images. We also present a whole registration method between EDI-OCT and SD-OCT images based on retinal thickness and Bruch's Membrane (BM) position. The CSJ surface is obtained with a 3D graph search in the CSJ feature space. ResultsExperimental results with 768 images (6 cubes, 128 B-scan images for each cube) from 2 healthy persons, 2 age-related macular degeneration (AMD) and 2 diabetic retinopathy (DR) patients, and 210 B-scan images from other 8 healthy persons and 21 patients demonstrate that our method can achieve high segmentation accuracy. The mean choroid volume difference and overlap ratio for 6 cubes between our proposed method and outlines drawn by experts were −1.96µm3 and 88.56%, respectively. ConclusionsOur method is effective for the 3D choroid segmentation of SD-OCT images because the segmentation accuracy and stability are compared with the manual segmentation.