Existing Image Segmentation Algorithms Research Articles

Machine Learning and Deep Learning Approach for Medical Image Analysis Summary Generator

Colorectal cancer, which is frequent, recognized tumours in both genders around the globe. As per the report generated by WHO in 2018, colon cancer placed in the third position, whereas 1.80 million individuals are affected. Precisely, it is the succeeding leading cancer, which is the second most common cause of cancer in females, and the third for males. The loss of control over the integrity of epidermal cells in bowel or malignancy can be the cause of colorectal cancer. An effective way to recognize colon cancer at an early stage and substantial treatment can reduce the ensuing death rates to a great extent. To perform Screening of Morphology of Malignant Tumor Cells in the colon, a Gastroenterologist may refer to cancer diagnosis tests for pathological images. In any Histology method, the process takes a significant duration of time due to infinite numbers of glands in the gastrointestinal system, which may lead to irreconcilable outcomes. By diagnosing through computer algorithms, can give practical and contributory results. Hence, accurate gland segmentation is one crucial prerequisite stage to get reliable and informative morphological image data. In recent times, the scholars applied machine learning algorithms to pathological image analysis for the diagnosis of cancer disease. We propose that features extracted from the diagnostic tests, given as input to a machine learning architecture used along with semantic segmentation algorithm, provide results that are accurate than the existing image segmentation algorithms. This work is the extensive review of machine learning architectures used for semantic segmentation on the histological images of the colon.In our project we will be using the following algorithms such as Adaboost as existing and Convolution Neural Network (CNN) as proposed and its accuracy is been calculated and well compared to other algorithms. It is found that CNN performs less than other algorithms

Real-Time Recognition of Molten Pools Based on Improved DeepLabV3+ in Keyhole Tungsten Inert Gas Welding Applications

During the Keyhole Tungsten Inert Gas (K-TIG) welding process, a significant amount of information related to the weld quality can be obtained from the weld pool and the keyhole of the topside molten pool image, which provides a vital basis for the control of welding quality. However, the topside molten pool image has the unstable characteristic of strong arc light, which leads to difficulty in contour extraction. The existing image segmentation algorithms cannot satisfy the requirements for accuracy, timing, and robustness. Aiming at these problems, a real-time recognition method, based on improved DeepLabV3+, for identifying the molten pool more accurately and effectively was proposed in this paper. First, MobileNetV2 was selected as the feature extraction network with which to improve detection efficiency. Then, the atrous rates of atrous convolution layers were optimized to reduce the receptive field and balance the sensitivity of the model to molten pools of different scales. Finally, the convolutional block attention module (CBAM) was introduced to improve the segmentation accuracy of the model. The experimental results verified that the proposed model had a fast segmentation speed and higher segmentation accuracy, with an average intersection ratio of 89.89% and an inference speed of 103 frames per second. Furthermore, the trained model was deployed in a real-time system and achieved a real-time performance of up to 28 frames per second, thus meeting the real-time and accuracy requirements of the K-TIG molten pool monitoring system.

Semi or fully automatic tooth segmentation in CBCT images: a review.

Cone beam computed tomography (CBCT) is widely employed in modern dentistry, and tooth segmentation constitutes an integral part of the digital workflow based on these imaging data. Previous methodologies rely heavily on manual segmentation and are time-consuming and labor-intensive in clinical practice. Recently, with advancements in computer vision technology, scholars have conducted in-depth research, proposing various fast and accurate tooth segmentation methods. In this review, we review 55 articles in this field and discuss the effectiveness, advantages, and disadvantages of each approach. In addition to simple classification and discussion, this review aims to reveal how tooth segmentation methods can be improved by the application and refinement of existing image segmentation algorithms to solve problems such as irregular morphology and fuzzy boundaries of teeth. It is assumed that with the optimization of these methods, manual operation will be reduced, and greater accuracy and robustness in tooth segmentation will be achieved. Finally, we highlight the challenges that still exist in this field and provide prospects for future directions.

Improved Procedure for the 3D Reconstruction of Asphalt Concrete Mesostructures Considering the Similarity of Aggregate Phase Geometry between Adjacent CT Slices.

Existing image segmentation algorithms used for the computed tomography (CT) images of asphalt concrete mostly ignore the similarity of aggregate phase geometry between adjacent CT slices, thus increasing the variability in the aggregate phase pixel values between adjacent slices and leading to a large number of model defects, e.g., interconnected aggregates, flaky aggregates, and incomplete aggregates. The developed mesostructural models with these defects pose a challenge to following simulation operations. To address this issue, an improved procedure for the 3D reconstruction of asphalt concrete mesostructures considering the similarity of aggregate phase geometry between adjacent slices was developed, which includes two adjacent-slice pixel-value-correction algorithms, a multi-directional multiple-correction method, and an image pixel interpolation process. First, the bilinear interpolation algorithm was employed to improve the pixel density of 2D CT images and the average filtering algorithm was used to reduce the noise of the CT images. Subsequently, the OTSU method was employed to separate the asphalt mortar matrix phase from the aggregate phase, and the marker-based watershed segmentation method was used to separate the interconnected aggregates. Finally, the adjacent-slice pixel-value-correction algorithm was used to recover the similarity of aggregate phase geometry between adjacent CT slices, and the multi-directional multiple-correction method was used to further enhance the geometric similarity. The results show that the developed 3D reconstruction procedure removes most of the model defects in the 3D mesostructural model of asphalt concrete, thus realistically maintaining the 3D spatial distribution features and contour characteristics.

A 3D Grouped Convolutional Network Fused with Conditional Random Field and Its Application in Image Multi-target Fine Segmentation

Aiming at the utilization of adjacent image correlation information in multi-target segmentation of 3D image slices and the optimization of segmentation results, a 3D grouped fully convolutional network fused with conditional random fields (3D-GFCN) is proposed. The model takes fully convolutional network (FCN) as the image segmentation infrastructure, and fully connected conditional random field (FCCRF) as the post-processing tool. It expands the 2D convolution into 3D operations, and uses a shortcut-connection structure to achieve feature fusion of different levels and scales, to realizes the fine-segmentation of 3D image slices. 3D-GFCN uses 3D convolution kernel to correlate the information of 3D image adjacent slices, uses the context correlation and probability exploration mechanism of FCCRF to optimize the segmentation results, and uses the grouped convolution to reduce the model parameters. The dice loss that can ignore the influence of background pixels is used as the training objective function to reduce the influence of the imbalance quantity between background pixels and target pixels. The model can automatically study and focus on target structures of different shapes and sizes in the image, highlight the salient features useful for specific tasks. In the mechanism, it can improve the shortcomings and limitations of the existing image segmentation algorithms, such as insignificant morphological features of the target image, weak correlation of spatial information and discontinuous segmentation results, and improve the accuracy of multi-target segmentation results and learning efficiency. Take abdominal abnormal tissue detection and multi-target segmentation based on 3D computer tomography (CT) images as verification experiments. In the case of small-scale and unbalanced data set, the average Dice coefficient is 88.8%, the Class Pixel Accuracy is 95.3%, and Intersection of Union is 87.8%. Compared with other methods, the performance evaluation index and segmentation accuracy are significantly improved. It shows that the proposed method has good applicability for solving typical multi-target image segmentation problems, such as boundary overlap, offset deformation and low contrast.

Retraction Note: Ocean detection and Japanese trade vocabulary translation based on remote sensing image boundary characteristics

Ocean detection plays an important role in ocean activities. The research of ocean detection plays an important supporting role in the theoretical research of ocean science, the protection, development, and utilization of ocean resources, and China’s maritime military issues. In this research, we propose a comprehensive ocean detection algorithm based on the boundary characteristics of the light and dark stripes of the internal waves in the SAR image. The results show that the algorithm can well identify the bright and dark stripes of ocean detection, not only can delete the outline of non-internal stripes, but also can delete some small but not obvious internal stripes. As an important method of image recognition, analysis, and understanding, image segmentation has been used by many scholars in previous image preprocessing. However, remote sensing images have the characteristics of wide-area observation, quasi real-time, and multi-band. If the traditional image segmentation algorithm is directly applied to the recognition and analysis of remote sensing images, the calculation time will be longer and the segmentation accuracy will be lower. Therefore, based on the analysis of existing image segmentation algorithms and combining the characteristics of remote sensing images (wide area coverage and multi-band), this paper proposes an ocean detection algorithm based on the boundary characteristics of remote sensing images. With the development of society and economy, the exchanges between countries have become increasingly close, and the market demand for translation talents is also increasing. This article analyzes the current situation of Japanese trade vocabulary translation teaching, points out that there are still many problems in Japanese trade vocabulary translation teaching, and proposes corresponding adjustment countermeasures, in order to improve the quality of Japanese trade vocabulary translation teaching and send qualified translators to the society.

Active contour model based on local intensity fitting and atlas correcting information for medical image segmentation

Intensity inhomogeneity and noises often occur in real medical images, which present a large degree of challenge to image segmentation. At the same time, most of the existing image segmentation algorithms are sensitive to initial conditions and model parameters. This paper presents an accurate and robust active contour model to solve the above problems. Inspired by the idea of the region-scalable fitting (RSF) model, we first define a local atlas fitting term transformed by the segmentation contour of the coherent local intensity clustering (CLIC) model. Then, we define a new energy functional by merging the atlas term into the energy functional of the RSF model. The advantage of this operation is that it makes full use of the existing segmentation features and advantages of the two models and avoids cumbersome adjustment of model parameters and initial contours. The experimental results clearly show that the improved model not only has better segmentation results than the RSF model and other active contour models such as the LINC, REGAC and SMAP models, but also solves the problem of sensitivity to initial contours, parameters adjustment and noise.

An improved segmentation algorithm of CT image based on U-Net network and attention mechanism

Medical image segmentation is one of the important steps in clinical diagnosis, and accurate segmentation of lesions is of great significance to clinical treatment. Therefore, a CT image segmentation algorithm based on depth learning is proposed to solve the problems of poor robustness, weak anti noise ability and low segmentation accuracy of existing image segmentation algorithms.. Firstly, we improve the u-net network structure, increase the batch standardization layer to improve the robustness of the network model, and introduce the attention mechanism to focus on specific things according to the needs, improve the recognition ability of the model. Then, the improved U-Net network structure is applied to CT image segmentation, and the cross entropy loss function is used to reduce the possibility of insufficient segmentation and segmentation leakage, and improve the accuracy of image segmentation. Finally, on the basis of data preprocessing, the segmentation network is trained to get the image segmentation model based on deep learning, and the prediction is made on the test set to get the segmentation results. The experimental results show that compared with other algorithms, the proposed method achieves 0.9594 in the common evaluation standard Dice coefficient, and has strong robustness. It can accurately segment the lung organs in CT images, which is helpful for doctors to obtain pathological information and assist in the diagnosis of lung diseases.

Multiobjective multiple features fusion: A case study in image segmentation

Most of existing image segmentation algorithms are only based on the color feature. However, the spatial distribution of an image can not be well described by using the color feature alone. Thus, it is necessary to add additional features to design efficient segmentation algorithms. Although many researchers also try to use multiple features for image segmentation, it is extremely difficult to combine multiple features automatically. This paper proposes a multiojective multiple features fusion strategy for image segmentation. The basic idea is to convert the segmentation problem into a multiobjective optimization problem, in which each objective considers one feature. It contains three steps. First, the original image is split into a set of over-segmented regions by using Meanshift to preserve the spatial details and to simplify the segmentation problem. Second, both the color and texture features are extracted to describe the regions. And two similarity matrices are designed by computing the similarity between each pair of regions in two features respectively. Third, a multiobjective evolutionary clustering algorithm is applied to merge these over-segmented regions. In this stage, two objective functions are designed based on the color and texture features respectively. A region index encoding scheme is introduced to design the individual, which contains some cluster representative regions. Some evolutionary operators are proposed to generate the new population. In the final generation, the best solution is selected from nondominated solutions for subsequent segmentation. Experiment results show that the proposed method provides promising segmentation results in combining the color and texture features.

Cardiac Image Segmentation Using Memory Persistence Methodology.

This paper presents a novel computer-aided framework for cardiac image segmentation using a methodology based on memory persistence. The primary concept is to mimic the process of human cognition in the segmentation of time-varying images (i.e., 2D + time or 3D + time), by remembering and exploiting results of previously segmented frames, to aid in segmentation of the region of interest with poor or ambiguous boundaries. The framework involves an intelligent image segmentation process which incorporates an automatic contour initialization mechanism, and a segmentation refinement mechanism that iteratively improves the segmentation results. The proposed framework is general and can integrate most existing image segmentation algorithms in the literature. The experimental results show the benefits of the proposed framework achieving insensitivity to contour initialization, high automation and better segmentation accuracy as compared to the original algorithm and its standard temporal constraint version.

АДАПТИВНИЙ МЕТОД СЕГМЕНТАЦІЇ ЗОБРАЖЕНЬ НА ОСНОВІ МЕТРИК

Проаналізовано сучасні алгоритми сегментації зображень, що дало змогу виділити їх переваги та недоліки для застосування в медичних цілях. Для діагностування передракових та ракових станів молочної залози використовують цитологічні та гістологічні зображення. Процес опрацювання таких зображень є важким і рутинним процесом, що потребує наявності спеціалізованих знань у медиків в галузі комп'ютерного зору. Недоліком біомедичних зображень є низька якість, неоднорідність освітлення у процесі формування зображень, низька контрастність. Неможливо застосувати одні і ті ж алгоритми і їх параметри до різних зображень, тому актуальним постає завдання розроблення адаптивних систем сегментації зображень. З'ясовано, що алгоритм сегментації методом водорозподілу у комбінації з методом порогової сегментації показав найкращі результати. Охарактеризовано закономірності між вхідними даними біомедичних зображень та алгоритмами сегментації. Сформовано правила нечіткої логіки для підбору параметрів алгоритмів біомедичних зображень. Розроблення автоматичної системи підбору параметрів сегментації цитологічних і гістологічних зображень є актуальним завданням, що підвищить якість опрацювання зображень.

Segmentation of Melanoma Skin Lesion Using Perceptual Color Difference Saliency with Morphological Analysis

The prevalence of melanoma skin cancer disease is rapidly increasing as recorded death cases of its patients continue to annually escalate. Reliable segmentation of skin lesion is one essential requirement of an efficient noninvasive computer aided diagnosis tool for accelerating the identification process of melanoma. This paper presents a new algorithm based on perceptual color difference saliency along with binary morphological analysis for segmentation of melanoma skin lesion in dermoscopic images. The new algorithm is compared with existing image segmentation algorithms on benchmark dermoscopic images acquired from public corpora. Results of both qualitative and quantitative evaluations of the new algorithm are encouraging as the algorithm performs excellently in comparison with the existing image segmentation algorithms.

Histogram-based image segmentation using variational mode decomposition and correlation coefficients

Image segmentation is defined by separating scenes into different parts. The grayscale histogram-based method is a widely used method in image segmentation because of its low computational complexity. However, traditional grayscale histogram-based methods usually suffer from wrong segmentation or low structure because of the irregularities and sharp details on the grayscale histogram and the absence of spatial information. This study presents an accurate image segmentation method by using the variational mode decomposition (VMD) and correlation coefficient (CC). First, grayscale histogram is decomposed into certain band-limit modes by VMD to remove the adverse effects. Then, the candidate centroids of the clusters are obtained by searching the refined histogram both vertically and horizontally. The K-means method is used to generate the segmentation results. Finally, some over-segmented regions are merged following the CCs of spatial histogram, which is also refined by the VMD method. The proposed method was applied to four images. The obtained experimental results show that the proposed method can generate reasonable segmentation results than those of the existing image segmentation algorithms.

Distance regularized level set evolution in magnetic resonance image segmention based on bi-dimensional ensemble empirical mode decomposition

Original image is directly processed by the existing image segmentation algorithms, which is easily affected by noise. A bi-dimensional ensemble empirical mode decomposition (BEEMD) method is introduced to improve the accuracy of MR image segmentation by distance regularized level set (DRLSE) method. The BEEMD method is the extension of one-dimensional noise assisted data analysis from ensemble empirical mode decomposition (EEMD). The key points of BEEMD are as follows. four-neighborhood optimization is used to find extermum; three-spline interpolation is used to obtain the envelope; amplitude standard of added white noise is restricted; a certain time of integration is used to avoid modality aliasing problem. The main steps of the proposed method are as follows. Firstly, the MR image is decomposed into a number of two-dimensional intrinsic mode functions (BIMF) by BEEMD method; different weighting coefficients are endued to BIMF for image reconstruction to enhance the segmentation target. Secondly, part of BIMF components are added into edge indicator function of DRLSE to recover the blurring boundary caused by Gauss smooth operation. Then DRLSE is used to segment the reconstructed MR image. High accuracy and robustness of proposed algorithm are obtained in both simulations and clinical MR images. However, compared with DRLSE, the proposed method is complex and time consuming because using BEEMD for preprocessing the segmentation image.

KmsGC: An Unsupervised Color Image Segmentation Algorithm Based onK-Means Clustering and Graph Cut

For unsupervised color image segmentation, we propose a two-stage algorithm, KmsGC, that combinesK-means clustering with graph cut. In the first stage,K-means clustering algorithm is applied to make an initial clustering, and the optimal number of clusters is automatically determined by a compactness criterion that is established to find clustering with maximum intercluster distance and minimum intracluster variance. In the second stage, a multiple terminal vertices weighted graph is constructed based on an energy function, and the image is segmented according to a minimum cost multiway cut. A large number of performance evaluations are carried out, and the experimental results indicate the proposed approach is effective compared to other existing image segmentation algorithms on the Berkeley image database.

A Noble Image Segmentation Using Local Area Splitting and Merging Method based on Intensity Change

This paper proposes a new image segmentation algorithm that involves local area splitting and merging based on intensity change. Most image segmentation algorithms take advantage of features such as pixel intensity and edge to split or merge an image. Therefore, in addition to susceptibility to noise, the latter algorithms have a problem in that they achieve different results depending on the initially selected seed location. The proposed method adaptively changes pixel intensity during the process of region segmentation to the representative intensity of the adjacent sub-area of high homogeneity. Therefore, this method is not affected by the initial seed location, and it also eliminates pre-process, such as noise removal, because the pixel intensity is progressively stabilized to the average value of object. In addition, this method preserves the edges of segmented objects and reduces the phenomenon of excessive region merger by determining the direction of the next merger upon splitting a local area into small sub-areas. Our experimental results demonstrated that the proposed method accurately segments images higher credibility than the existing image segmentation algorithms.

3D Superalloy Grain Segmentation Using a Multichannel Edge-Weighted Centroidal Voronoi Tessellation Algorithm

Accurate grain segmentation on 3D superalloy images is very important in materials science and engineering. From grain segmentation, we can derive the underlying superalloy grains' micro-structures, based on how many important physical, mechanical, and chemical properties of the superalloy samples can be evaluated. Grain segmentation is, however, usually a very challenging problem because: 1) even a small 3D superalloy sample may contain hundreds of grains; 2) carbides and noises may degrade the imaging quality; and 3) the intensity within a grain may not be homogeneous. In addition, the same grain may present different appearances, e.g., different intensities, under different microscope settings. In practice, a 3D superalloy image may contain multichannel information where each channel corresponds to a specific microscope setting. In this paper, we develop a multichannel edge-weighted centroidal Voronoi tessellation (MCEWCVT) algorithm to effectively and robustly segment the superalloy grains from 3D multichannel superalloy images. MCEWCVT performs segmentation by minimizing an energy function, which encodes both the multichannel voxel-intensity similarity within each cluster in the intensity domain and the smoothness of segmentation boundaries in the 3D image domain. In the experiment, we first quantitatively evaluate the proposed MCEWCVT algorithm on a four-channel Ni-based 3D superalloy data set (IN100) against the manually annotated ground-truth segmentation. We further evaluate the MCEWCVT algorithm on two synthesized four-channel superalloy data sets. The qualitative and quantitative comparisons of 18 existing image segmentation algorithms demonstrate the effectiveness and robustness of the proposed MCEWCVT algorithm.

Segmentation of clustered nuclei based on concave curve expansion

Segmentation of nuclei from images of tissue sections is important for many biological and biomedical studies. Many existing image segmentation algorithms may lead to oversegmentation or undersegmentation for clustered nuclei images. In this paper, we proposed a new image segmentation algorithm based on concave curve expansion to correctly and accurately extract markers from the original images. Marker-controlled watershed is then used to segment the clustered nuclei. The algorithm was tested on both synthetic and real images and better results are achieved compared with some other state-of-the-art methods.

Multispectral textured image segmentation using a multi-resolution fuzzy Markov random field model on variable scales in the wavelet domain

This article proposes a new multispectral image texture segmentation algorithm using a multi-resolution fuzzy Markov random field model for a variable scale in the wavelet domain. The algorithm considers multi-scalar information in both vertical and lateral directions. The feature field of the scalable wavelet coefficients is modelled, combining with the fuzzy label field describing the spatially constrained correlations between neighbourhood features to achieve a more accurate parameter estimation. The extended scalable label field models the label data from different scales to obtain more homogeneous areas; image segmentation results are finally obtained according to the Bayesian rule from a coarser to a finer scale. Multispectral texture images and remote-sensing images are used to test the effectiveness of the the proposed method. Segmentation results show that the new method simultaneously presents a better performance in achieving the homogeneity of the region and accuracy of detected boundaries compared with existing image segmentation algorithms.

Level Set Method for Image Segmentation: A Survey

A considerable challenge in image segmentation in real world images is intensity inhomogenity. The existing image segmentation algorithms rely on region based and it typically features similarity of image intensities in the region of interest. Due to the presence of intensity non uniformity the segmentation results are not accurate. So this survey paper gives a novel region based techniques for image segmentation in the presence of intensity inhomogenity. Intensity non uniformity occurs in real world images due to various factors such as spatial variations on illumination, imperfections of imaging devices, noise and of low contrast, causes many problems in image processing and computer vision. Image segmentation is a very difficult task in the presence of non uniformity of intensities. Intensity non uniformity is caused by the overlaps between the ranges of intensities in the region to be segmented. This paper covers segmentation techniques to overcome the intensity inhomogenity with the help of Level Set Method. The aim is to implement a level set approach for active contour image segmentation for MRI images. No requirement about object's shape and allowances for very flexible topology change are key advantages for this method. As an application our method can be used for