It is important for the early diagnosis and treatment of lung cancer in the computer-aided Diagnosis/Detection（cAD） system, and accurate segmentation of pulmonary nodules from tomographic images is the basic and act...
详细信息
It is important for the early diagnosis and treatment of lung cancer in the computer-aided Diagnosis/Detection（cAD） system, and accurate segmentation of pulmonary nodules from tomographic images is the basic and active research problem for the benign or malign diagnosis. For this reason, this work seeks to develop automatic detection and classification method of lung nodules. First, the algorithm separates lung parenchyma from the anatomical structures based on maximum between-cluster variance, image dilation and erosion. Secondly, a modified robust fuzzyc-meansclustering（r FcM） segmentation algorithm is proposed, this method improves the objective function by adding a punishment factor, for eliminating the influence from noise and non-uniform gray problem. Experimental results have shown that the proposed method can achieve more accurate segmentation and perform better than other traditional algorithms in classification and recognition, Furthermore, the segmentation results on brain images also get a satisfied performance.
The classification recognition performance is a hot study in the field of remote sensing image. In this paper, texture feature, shape feature, radiation intensity of remote sensing image information were used to initi...
详细信息
ISBN:
(纸本)9781509034840
The classification recognition performance is a hot study in the field of remote sensing image. In this paper, texture feature, shape feature, radiation intensity of remote sensing image information were used to initial terrain classification. Then an improved fuzzy c-means algorithm was applied on classification, and it included optimization of determine clustering center, got the number of clustering automatically and removed the noise of image after classification. Meanwhile, as an alternative to expert knowledge, data fusion method was used, which included the fusion of aeromagnetic data, gravity data and elevation data. The empirical results showed that this method can avoid the highly dependent on domain knowledge experts in image recognition and got a better classification effect in remote sensing image.
fuzzyc-means (FcM) algorithm is widely used for unsupervised image segmentation. However, the FcM algorithm does not take into account the local information in the image context. This makes the FcM algorithm sensitiv...
详细信息
ISBN:
(纸本)9781509041145
fuzzyc-means (FcM) algorithm is widely used for unsupervised image segmentation. However, the FcM algorithm does not take into account the local information in the image context. This makes the FcM algorithm sensitive to additive noise degrading the image pixels features. In this paper, an approach to incorporating local data context and membership information into the FcM is presented. The approach consists of adding a weighted regularization function to the standard FcM algorithm. This function is formulated to resemble the standard FcM objective function but the distance is replaced by a new one generated from the local complement or residual membership. The applied regularizing weight is a constant weight or alternatively an adaptive one. The adaptive weight is the Euclidian distance between the center prototype and the local image data mean. The regularizing function aims at smoothing out additive noise and biasing the clustered image to piecewise homogenous regions. Simulation results of clustering and segmentation of synthetic and real-world noisy images have been presented. These results have shown that the presented approach enhances the performance of the FcM algorithm in comparison with the standard FcM and several previously modified FcM algorithms.
Breast cancer is one of the most incurable diseases, which leads to the death of women globally every year. For initial detection of a tumor in the breast, the most useful technique called 'Mammography' is use...
详细信息
ISBN:
(纸本)9781509020287
Breast cancer is one of the most incurable diseases, which leads to the death of women globally every year. For initial detection of a tumor in the breast, the most useful technique called 'Mammography' is used, which is an X-ray inspection of the breast, which can be used to detect the breast tumor which may lead to breast cancer. Using Mammography, a small lump that may lead to breast cancer can be detected at the initial stage. Sometimes it is not possible to recognize very small tumors because of noisy, blurred, and fuzzy images. Therefore, they need to be enhanced to increase the contrast for better visual perception and reduce the noise from it for better diagnosis. In this work, FcM algorithm is used to detect the suspicious lesions in a mammogram. To achieve the objective of this work, MIAS (Mammographic Image Analysis Society) and INbreast databases are used, which contain 322 and 412 images of the breast (both left and right breast) respectively. In these databases, every image is examined by the expert radiologists. The effectiveness of the algorithm is measured in terms of MSE and PSNR.
cluster analysis is a useful tool used commonly in data analysis. The purpose of cluster analysis is to separate data sets into subsets according to their similarities and dissimilarities. In this paper, the fuzzyc-m...
详细信息
cluster analysis is a useful tool used commonly in data analysis. The purpose of cluster analysis is to separate data sets into subsets according to their similarities and dissimilarities. In this paper, the fuzzy c-means algorithm was adapted for directional data. In the literature, several methods have been used for the clustering of directional data. Due to the use of trigonometric functions in these methods, clustering is performed by approximate distances. As opposed to other methods, the FcM4DD uses angular difference as the similarity measure. Therefore, the proposed algorithm is a more consistent clustering algorithm than others. The main benefit of FcM4DD is that the proposed method is effectively a distribution-free approach to clustering for directional data. It can be used for N-dimensional data as well as circular data. In addition to this, the importance of the proposed method is that it would be applicable for decision making process, rule-based expert systems and prediction problems. In this study, some existing clustering algorithms and the FcM4DD algorithm were applied to various artificial and real data, and their results were compared. As a result, these comparisons show the superiority of the FcM4DD algorithm in terms of consistency, accuracy and computational time. fuzzyclustering algorithms for directional data (FcM4DD and FcD) were compared according to membership values and the FcM4DD algorithm obtained more acceptable results than the FcD algorithm. (c) 2016 Elsevier Ltd. All rights reserved.
The classification recognition performance is a hot study in the field of remote sensing image. In this paper, texture feature, shape feature, radiation intensity of remote sensing image information were used to initi...
详细信息
The classification recognition performance is a hot study in the field of remote sensing image. In this paper, texture feature, shape feature, radiation intensity of remote sensing image information were used to initial terrain classification. Then an improved fuzzy c-means algorithm was applied on classification, and it included optimization of determine clustering center, got the number of clustering automatically and removed the noise of image after classification. Meanwhile, as an alternative to expert knowledge, data fusion method was used, which included the fusion of aeromagnetic data, gravity data and elevation data. The empirical results showed that this method can avoid the highly dependent on domain knowledge experts in image recognition and got a better classification effect in remote sensing image.
Breast cancer is one of the most incurable diseases, which leads to the death of women globally every year. For initial detection of a tumor in the breast, the most useful technique called 'Mammography' is use...
详细信息
ISBN:
(纸本)9781509020300
Breast cancer is one of the most incurable diseases, which leads to the death of women globally every year. For initial detection of a tumor in the breast, the most useful technique called 'Mammography' is used, which is an X-ray inspection of the breast, which can be used to detect the breast tumor which may lead to breast cancer. Using Mammography, a small lump that may lead to breast cancer can be detected at the initial stage. Sometimes it is not possible to recognize very small tumors because of noisy, blurred, and fuzzy images. Therefore, they need to be enhanced to increase the contrast for better visual perception and reduce the noise from it for better diagnosis. In this work, FcM algorithm is used to detect the suspicious lesions in a mammogram. To achieve the objective of this work, MIAS (Mammographic Image Analysis Society) and INbreast databases are used, which contain 322 and 412 images of the breast (both left and right breast) respectively. In these databases, every image is examined by the expert radiologists. The effectiveness of the algorithm is measured in terms of MSE and PSNR.
A thermally grown oxide (TGO) layer of Al2O3 is formed between a coNicrAlY bond coating and a zirconia top coating of a thermal barrier coating (TBc) system on an Inconel 738 substrate during exposure at 1050 degrees ...
详细信息
A thermally grown oxide (TGO) layer of Al2O3 is formed between a coNicrAlY bond coating and a zirconia top coating of a thermal barrier coating (TBc) system on an Inconel 738 substrate during exposure at 1050 degrees c. Thick TGO is vulnerable to damage in terms of cracking and spallation. In order to estimate the TBc failure, fundamental damage data of TGO that is induced by compressed air are monitored to determine the failure mode and the state of damage by using a nondestructive acoustic emission (AE) system. The defects of the TGO are detected and evaluated by means of AE signal analysis with the root mean squared value in the frequency range of 100 kHz to 400 kHz. The thickness of the TGO increased with the oxidation time. The RMS (Root Mean Square) value decreased almost linearly as the TGO thickness increased up to the failure of the TBc. The amplitude of the AE signal decreased dramatically when the TGO was delaminated. The AE signals for pattern classification were evaluated in accordance with the TBc layer. It is conceivable that the center value represents the damage state of the TBccoating.
Due to advances in information technology, data collection is becoming much easier. clustering is an important technique for exploring data structures used in many fields, such as customer segmentation, image recognit...
详细信息
Due to advances in information technology, data collection is becoming much easier. clustering is an important technique for exploring data structures used in many fields, such as customer segmentation, image recognition, social science, and so on. However, in real-world applications, there are a lot of noises or outliers which will seriously influence the clustering performance in the dataset. Besides, the clustering results are susceptible to the initial centroids and algorithm parameters. To overcome the influence of outliers on clustering results, this study combines the advantages of probability c-means and fuzzyc-ordered means to propose a fuzzy possibilisticc-ordered means (FPcOM) algorithm. In order to solve the problem of parameters and initial centroids determination, this study employs a sine cosine algorithm (ScA) combined with FPcOM to improve the clustering results. The proposed algorithm is named ScA-FPcOM algorithm. Ten benchmark datasets collected from the UcI machine repository were used to validate the proposed algorithm in terms of adjusted rand index and the Silhouette coefficient. According to the experimental results, the ScA-FPcOM algorithmcan obtain better results than other algorithms.
Image segmentation allows us to separate an image into distinct, non-overlapping parts by utilizing specific features such as hue, texture, and shape. The technique is prevalent in different domains, including target ...
详细信息
Image segmentation allows us to separate an image into distinct, non-overlapping parts by utilizing specific features such as hue, texture, and shape. The technique is prevalent in different domains, including target detection, medical imaging, and pattern recognition owing to its importance in analyzing the image. The fuzzyc-means (FcM) algorithm is a popular method for image segmentation and pattern recognition. However, uncertainty and unknown noise in the data impair the effectiveness of the algorithm. Alternatively, uncertainty in real world can be addressed by the intuitionisticfuzzy set (IFS). This article presents a new approach to image representation using IFS and local information about the image. We introduce the concept of filtering into the intuitionisticfuzzy set and utilize a specially designed exponential distance for IFS. We propose the intuitionisticfuzzy local information c-means (IFLIcM) algorithm. The goal of IFLIcM is to increase the tolerance to noise and the maintain the details in image better than existing FcM variants. We test the performance of our algorithm on a public dataset and compare it with existing FcM methods and Double Deep-Image-Prior (Double-DIP). The experimental results demonstrate that IFLIcM is highly effective in image segmentation and outperforms existing methods.
暂无评论