检索结果-内蒙古大学图书馆

unsupervised image segmentation with Gaussian Pairwise Markov Fields

COMPUTATIONAL STATISTICS & DATA ANALYSIS 2021年 158卷 107178-107178页

作者： Gangloff, Hugo Courbot, Jean-Baptiste Monfrini, Emmanuel Collet, Christophe Univ Strasbourg CNRS ICube UMR 7357 300 Bd Sebastien Brant F-67400 Illkirch Graffenstaden France GEPROVAS Strasbourg France Univ Haute Alsace IRIMAS UR 7499 Mulhouse France Inst Polytech Paris Telecom SudParis SAMOVAR Palaiseau France

Modeling strongly correlated random variables is a critical task in the context of latent variable models. A new probabilistic model, called Gaussian Pairwise Markov Field, is presented to generalize existing Markov Fields latent variables models, and to introduce more correlations between variables. This is done by considering the correlations within Gaussian Markov Random Fields models which are much richer than in the classical Markov Field models. The assets of the Gaussian Pairwise Markov Field model are explained. In particular, it offers a generalization of the classical Markov Field modelization that is highlighted. The new model is also considered in the practical case of unsupervised segmentation of images corrupted by long-range spatially-correlated noise, producing interesting new results. (C) 2021 Elsevier B.V. All rights reserved.

关键词： unsupervised image segmentation Pairwise Markov Fields Gaussian Markov Fields Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Multi-view Clustering for unsupervised image segmentation 30th

Self-supervised Multi-view Clustering for Unsupervised Image...

引用

30th International Conference on Artificial Neural Networks (ICANN)

作者： Fang, Tiyu Liang, Zhen Shao, Xiuli Dong, Zihao Li, Jinping Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China Nankai Univ Coll Comp Sci Tianjin 300350 Peoples R China

ISBN: (纸本)9783030863838;9783030863821

At present, the main idea of CNN-based unsupervised image segmentation is clustering a single image in the framework of CNNs. However, the single image clustering is very difficult to obtain enough supervision information for network learning. For solving this problem, we propose a Self-supervised Multi-view Clustering (SMC) structure for unsupervised image segmentation to mine additional supervised information. Based on the observation that the predicted pixel-level labels and the input images have the same spatial features, the multi-view images acquired by data augmentation are clustered to obtain the multi-view results and the proposed SMC uses the differences among these results to learn self-supervised information. Moreover, a Hybrid Self-supervised (HS) loss is proposed to make full use of the self-supervised information for further improving the prediction accuracy and the convergence speed. Extensive experiments in BSD500 and PASCAL VOC 2012 datasets demonstrate the superiority of our proposed approach.

关键词： unsupervised image segmentation Convolutional neural network Self-supervised Multi-view Clustering

来源：评论

学校读者我要写书评

暂无评论

Semantic Guided Deep unsupervised image segmentation 20th

Semantic Guided Deep Unsupervised Image Segmentation

引用

20th International Conference on image Analysis and Processing (ICIAP)

作者： Saha, Sudipan Sudhakaran, Swathikiran Banerjee, Biplab Pendurkar, Sumedh Fdn Bruno Kessler Trento Italy Univ Trento Trento Italy Indian Inst Technol Mumbai Maharashtra India Coll Engn Pune Pune Maharashtra India

ISBN: (纸本)9783030306458;9783030306441

image segmentation is an important step in many image processing tasks. Inspired by the success of deep learning techniques in image processing tasks, a number of deep supervised image segmentation algorithms have been proposed. However, availability of sufficient labeled training data is not plausible in many application domains. Some application domains are even constrained by the shortage of unlabeled data. Considering such scenarios, we propose a semantic guided unsupervised Convolutional Neural Network (CNN) based approach for image segmentation that does not need any labeled training data and can work on single image input. It uses a pre-trained network to extract mid-level deep features that capture the semantics of the input image. Extracted deep features are further fed to trainable convolutional layers. segmentation labels are obtained using argmax classification of the final layer and further spatial refinement. Obtained segmentation labels and the weights of the trainable convolutional layers are jointly optimized in iterations in a mechanism that the deep network learns to assign spatially neighboring pixels and pixels of similar feature to the same label. After training, the input image is processed through the same network to obtain the labels that are further refined by a segment score based refinement mechanism. Experimental results show that our method obtains satisfactory results inspite of being unsupervised.

关键词： unsupervised image segmentation Semantic guided Deep learning

来源：评论

学校读者我要写书评

暂无评论

An unsupervised image segmentation Workflow for Extraction of Left Coronary Artery from X-Ray Coronary Angiography 1

引用

2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI)

作者： Dasic, Lazar Pavic, Ognjen Geroski, Tijana Filipovic, Nenad Univ Kragujevac Inst Informat Technol Jovana Cvijica Bb Kragujevac 34000 Serbia Bioengn Res & Dev Ctr BioIRC Prvoslava Stojanovica 6 Kragujevac 34000 Serbia Univ Kragujevac Fac Engn Sestre Janjic 6 Kragujevac 34000 Serbia

ISBN: (数字)9783031608407

ISBN: (纸本)9783031608391;9783031608407

Coronary heart disease (CHD) is a serious cardiovascular illness that is among the top causes of death worldwide. Using X-ray coronary angiography, it is possible to detect and monitor CHD by visualizing coronary vessels. One of the most important steps in analyzing angiographic images is image segmentation, where the coronary arteries are separated from the background. In this paper, we propose an unsupervised image segmentation workflow that uses different filters in order to minimize the limitations of X-ray coronary angiography and achieve satisfactory segmentation of the left coronary artery. During the preprocessing step, the X-ray angiographic image of the coronary artery is processed with CLAHE, the Wiener filter and gamma correction in order to overcome the shortcomings of the X-ray imaging data. These preprocessing steps greatly reduce the background noise and improve the separation of the artery from the rest of the image. The preprocessed image is then segmented using Otsu's thresholding method, which results in a binarized image. This image has left coronary artery successfully segmented, but unfortunately a lot of non-vessel segments have been wrongly labeled as well. In the postprocessing step, connected components are obtained, and then using information about their size the largest connected component represents a segmented left coronary artery, while the rest is marked as background.

关键词： left coronary artery unsupervised image segmentation x-ray coronary angiography

来源：评论

学校读者我要写书评

暂无评论

Adaptive Non-local Affinity Graph for unsupervised image segmentation

Adaptive Non-local Affinity Graph for Unsupervised Image Seg...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Lv, Xin Su, Zhenming Zhang, Taiyi Cheng, Wenxiang Qi, Xiaoqiong Lanzhou Univ Sch Informat Sci & Engn Lanzhou Peoples R China Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld Australia

ISBN: (纸本)9781665468916

In this paper, we present an adaptive superpixel-based graph construction method for unsupervised image segmentation. The empirical findings in this study provide a new understanding of applying non-local image patches to image segmentation. We demonstrate that high-level segmentation cues can be revealed by non-local similar patches, and based on it the similarity between superpixels overlapped with these similar patches can be adaptively constructed. The experimental result on the Berkeley segmentation Database demonstrates the effectiveness and superiority of the proposed algorithm.

关键词： unsupervised image segmentation graph construction spectral segmentation

来源：评论

学校读者我要写书评

暂无评论

unsupervised image segmentation based on multidimensional particle swarm optimization

Unsupervised image segmentation based on multidimensional pa...

引用

6th International Conference on Wireless, Mobile and Multi-Media (ICWMMN 2015)

作者： Lin Wang Wanxu Zhang Dong Wang Bo Jiang School of Information Science and Technology Northwest University Xi'an 710127 China School of Computer and Information Technology Beijing Jiaotong University 100044 China

ISBN: (纸本)9781510822030

An unsupervised image segmentation method based on multidimensional (MD) particle swarm optimization (PSO) is proposed in this paper. Firstly, a clustering-based nonlinear objective function of unsupervised image segmentation is established according to Turi's validity index. Secondly, MD PSO algorithm is adopted to minimize the objective function to seek the optimal number and cluster centers of segmented regions simultaneously. Finally, global best (GB) position of swam in each dimension is modified to avoid being trapped in local optima. Experimental results valid the performance of the proposed image segmentation algorithm.

关键词： unsupervised image segmentation Turi's validity index Multidimensional PSO image segmentation Particle swarm optimization image segmentation algorithm MULTIDIMENSIONAL Objective function parametric subharmonic oscillator dimensions

来源：评论

学校读者我要写书评

暂无评论

AN unsupervised image segmentation ALGORITHM BASED ON THE MACHINE LEARNING OF APPROPRIATE FEATURES

AN UNSUPERVISED IMAGE SEGMENTATION ALGORITHM BASED ON THE MA...

引用

16th IEEE International Conference on image Processing

作者： Lee, Sang Hak Koo, Hyung Il Cho, Nam Ik Seoul Natl Univ Dept Elect Engn & Comp Sci Seoul 151 South Korea

ISBN: (纸本)9781424456536

This paper proposes a new approach to the feature based unsupervised image segmentation. The difficulty with the conventional unsupervised segmentation lies in finding appropriate features that discriminate a meaningful region from the others. In this paper, the appropriate features are automatically learnt by machine learning with boosting scheme. At the initial step, the image is split into many small regions (blocks at first) and strong classifiers for every region, which discriminate the region from the others, are found by AdaBoosting. Each strong classifier so obtained is the weighted sum of several popular weak classifiers (features), which best describes the coherence of the region and thus well discriminates the region from the others. The output of this classifier is used in designing the energy function for the labeling, in the form of Conditional Random Fields (CRFs). Minimization of the energy function produces the labeling result which reflects the property learnt by the classifier. For the labeling result, the machine learning is again performed and the process iterates until some conditions are met. Experimental results show that the proposed method provides competitive result compared to the conventional feature based methods.

关键词： unsupervised image segmentation machine learning AdaBoost EM-like minimization

来源：评论

学校读者我要写书评

暂无评论

Convergence of unsupervised image segmentation algorithms

Convergence of unsupervised image segmentation algorithms

引用

Conference on Neural, Morphological, and Stochastic Methods in image and Signal Processing

作者： WON, CS DONGGUK UNIV DEPT ELECTR ENGNSEOUL 100715SOUTH KOREA

ISBN: (纸本)0819419273

This paper presents a comparative study of three deterministic unsupervised image segmentation algorithms. All of the three algorithms basically make use of a Markov random field (MRF) and try to obtain an approximate solution to the maximum likelihood or the maximum a posteriori estimates. Although the three algorithms are based on the same stochastic image models, they adopt different ways to incorporate model parameter estimation into the iterative region label updating procedure. The differences among the three algorithms are identified and the convergence properties are compared both analytically and experimentally.

关键词： unsupervised image segmentation MARKOV RANDOM FIELDS GRIBBS RANDOM FIELDS MAXIMUM LIKELIHOOD ESTIMATION MAXIMUM A POSTERIORI ESTIMATION ITERATED CONDITIONAL MODES EXPECTATION AND MAXIMIZATION

来源：评论

学校读者我要写书评

暂无评论

unsupervised image segmentation Using Comparative Reasoning and Random Walks

Unsupervised Image Segmentation Using Comparative Reasoning ...

引用

IEEE Global Conference on Signal and Information Processing

作者： Anuva Kulkarni Filipe Condessa Jelena Kovacevic Department of Electrical and Computer Engineering Carnegie Mellon University Department of Electrical and Computer Engineering

ISBN: (纸本)9781479975921

An image segmentation method that does not need training data can provide faster results than methods using complex optimization. Motivated by this idea, we present an unsupervised image segmentation method that combines comparative reasoning with graph-based clustering. Comparative reasoning enables fast similarity search on the image, and these search results are used with the Random Walks algorithm, which is used for clustering and calculating class probabilities. Our method is validated on diverse image modalities such as biomedical images, natural images and texture images. The performance of the method is measured through cluster purity based on available ground truth. Our results are compared to existing segmentation methods using Global Consistency Error scores.

关键词： unsupervised image segmentation hashing Winner Take All hash comparative reasoning Random Walks

来源：评论

学校读者我要写书评

暂无评论

Deep expectation-maximization network for unsupervised image segmentation and clustering

引用

image AND VISION COMPUTING 2023年第1期135卷

作者： Pu, Yannan Sun, Jian Tang, Niansheng Xu, Zongben Key Lab Stat Modeling & Data Anal Yunnan Prov Kunming Peoples R China Xi An Jiao Tong Univ Xian Peoples R China

unsupervised learning, such as unsupervised image segmentation and clustering, are fundamental tasks in image representation learning. In this paper, we design a deep expectation-maximization (DEM) network for unsuper-vised image segmentation and clustering. It is based on the statistical modeling of image in its latent feature space by Gaussian mixture model (GMM), implemented in a novel deep learning framework. Specifically, in the unsu-pervised setting, we design an auto-encoder network and an EM module over the image latent features, for jointly learning the image latent features and GMM model of the latent features in a single framework. To con-struct the EM-module, we unfold the iterative operations of EM algorithm and the online EM algorithm in fixed steps to be differentiable network blocks, plugged into the network to estimate the GMM parameters of the image latent features. The proposed network parameters can be end-to-end optimized using losses based on log-likelihood of GMM, entropy of Gaussian component assignment probabilities and image reconstruction error. Extensive experiments confirm that our proposed networks achieve favorable results compared with sev-eral state-of-the-art methods in unsupervised image segmentation and clustering.& COPY;2023 Elsevier B.V. All rights reserved.

关键词： Deep clustering EM algorithm image clustering Representation learning unsupervised image segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：