检索结果-内蒙古大学图书馆

A Nonsymmetric Mixture Model for unsupervised image segmentation

IEEE TRANSACTIONS ON CYBERNETICS 2013年第2期43卷 751-765页

作者： Thanh Minh Nguyen Wu, Q. M. Jonathan Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada

Finite mixture models with symmetric distribution have been widely used for many computer vision and pattern recognition problems. However, in many applications, the distribution of the data has a non-Gaussian and nonsymmetric form. This paper presents a new nonsymmetric mixture model for image segmentation. The advantage of our method is that it is simple, easy to implement, and intuitively appealing. In this paper, each label is modeled with multiple D-dimensional Student's t-distribution, which is heavily tailed and more robust than Gaussian distribution. Expectation-maximization algorithm is adopted to estimate model parameters and to maximize the lower bound on the data log-likelihood from observations. Numerical experiments on various data types are conducted. The performance of the proposed model is compared with that of other mixture models, demonstrating the robustness, accuracy, and effectiveness of our method.

关键词： Expectation-maximization (EM) algorithm non-Gaussian distribution nonsymmetric mixture model (NSMM) unsupervised image segmentation

来源：评论

学校读者我要写书评

暂无评论

Sparse depth densification for monocular depth estimation

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第5期83卷 14821-14838页

作者： Liang, Zhen Fang, Tiyu Hu, Yanzhu Wang, Yingjian Beijing Univ Posts & Telecommun Beijing Key Lab Work Safety Intelligent Monitoring Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Sch Modern Post Sch Automat Beijing 100876 Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250100 Peoples R China

Now the dense depth prediction by single image and a few sparse depth measurements has attracted more and more attention because it provides a low-cost and efficient solution for estimating high-quality depth information. But the current existing methods for the field only take sparse depth as an independent dimension, and the relationship between sparse depth and image itself is always ignored, which undoubtedly limits the improvement of prediction accuracy. For solving the problem, in this paper, a sparse depth densification method is proposed to fully mine the relationship between sparse depth and image for achieving more accurate depth estimation. Based on a priori that the object areas of same category have similar depth values, a Depth Densification Map (DDM) is constructed by the segmentation label obtained from unsupervised image segmentation and sparse depth to realize sparse depth densification. Meantime, considering the potential error of DDM, a Depth Error Map (DEM) is designed to further correct DDM. Then, we use the idea of multi-scale fusion to build a depth estimation network. Finally, the proposed maps are combined with single image as the input of the network, and used to carry out the actual training and testing. Extensive experiments on NYU Depth v2 and Make3D datasets demonstrate the superiority of our proposed approach. Our code is available at . .

关键词： Monocular depth estimation unsupervised image segmentation Sparse depth densification Multi-scale fusion

来源：评论

学校读者我要写书评

暂无评论

unsupervised leaf segmentation in complex backgrounds using mutual information minimization

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2023年第6期45卷 10127-10139页

作者： Guo, Yijian Sun, Kaiqiong Luo, Gang Wang, Meng Wuhan Polytech Univ Sch Math & Comp Sci Wuhan 430023 Peoples R China

Leaf segmentation is crucial for plant recognition, especially for tree species identification. In natural environments, leaf segmentation can be very challenging due to the lack of prior information about leaves and the variability of backgrounds. In typical applications, supervised algorithms often require pixel-level annotation of regions, which can be labour-intensive and limited to identifying plant species using pre-labelled samples. On the other hand, traditional unsupervised image segmentation algorithms require specialised parameter tuning for leaf images to achieve optimal results. Therefore, this paper proposes an unsupervised leaf segmentation method that combines mutual information with neural networks to better generalise to unknown samples and adapt to variations in leaf shape and appearance to distinguish and identify different tree species. First, a model combining a Variational Autoencoder (VAE) and a segmentation network is used as a pre-segmenter to obtain dynamic masks. Secondly, the dynamic masks are combined with the segmentation masks generated by the mask generator module to construct the initial mask. Then, the patcher module uses the Mutual Information Minimum (MIM) loss as an optimisation objective to reconstruct independent regions based on this initial mask. The process of obtaining dynamic masks through pre-segmentation is unsupervised, and the entire experimental process does not involve any label information. The experimental method was performed on tree leaf images with a naturally complex background using the publicly available Pl@ntLeaves dataset. The results of the experiment showed that compared to existing excellent methods on this dataset, the IoU (Intersection over Union) index increased by 3.9%.

关键词： Leaf extraction deep learning unsupervised image segmentation mutual information VAE

来源：评论

学校读者我要写书评

暂无评论

Fast image segmentation with Contextual Scan and Markov Chains 29

Fast Image Segmentation with Contextual Scan and Markov Chai...

引用

29th European Signal Processing Conference (EUSIPCO)

作者： Fernandes, Clement Monti, Thomas Monfrini, Emmanuel Pieczynski, Wojciech Segula Matra Automot Dept Elect & Syst Trappes France Inst Polytech Paris Dept CITI Telecom Sudparis Evry France

ISBN: (纸本)9789082797060

Transforming bi-dimensional images into mono-dimensional sequences with Peano scan (PS) allows using Hidden Markov Chains (HMCs) for unsupervised image segmentation. In some situations, such methods can be competitive compared to Hidden Markov Fields (HMFs) based ones, while being much faster. We propose enriching the HMC-PS model by introducing "contextual" Peano scan (CPS). It consists in associating to each index in the HMC obtained from PS, two observations on pixels which are neighbors of the pixel considered in the image, but are not its neighbors in the HMC. This gives three observations on each point of the Peano scan, which leads to a new HMC with a more complex structure, but whose prior and posterior laws are still Markovian. Therefore we can apply the usual parameter estimation method: Stochastic Expectation-Maximization (SEM), as well as study unsupervised segmentation Marginal Posterior Mode (MPM) so obtained. The CPS based supervised and unsupervised MPM are compared to the classic scan based HMC-PS and the HMF through experiments on artificial images. They improve notably the former, and can even compete with the latter.

关键词： hidden Markov chains Peano scan unsupervised image segmentation contextual Peano scan SEM

来源：评论

学校读者我要写书评

暂无评论

unsupervised Camouflaged Object segmentation as Domain Adaptation

Unsupervised Camouflaged Object Segmentation as Domain Adapt...

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Zhang, Yi Wu, Chengyi Ecole Technol Super LIVIA Montreal PQ Canada Henan Polytech Univ Jiaozuo Henan Peoples R China

ISBN: (纸本)9798350307443

Deep learning for unsupervised image segmentation remains challenging due to the absence of human labels. The common idea is to train a segmentation head, with the supervision of pixel-wise pseudo-labels generated based on the representation of self-supervised backbones. By doing so, the model performance depends much on the distance between the distribution of target datasets, and the one of backbones' pre-training dataset (e.g., imageNet). In this work, we investigate a new task, namely unsupervised camouflaged object segmentation (UCOS), where the target objects own a common rarely-seen attribute, i.e., camouflage. Unsurprisingly, we find that the state-of-the-art unsupervised models struggle in adapting UCOS, due to the domain gap between the properties of generic and camouflaged objects. To this end, we formulate the UCOS as a source-free unsupervised domain adaptation task (UCOS-DA), where both source labels and target labels are absent during the whole model training process. Specifically, we define a source model consisting of self-supervised vision transformers pre-trained on imageNet. On the other hand, the target domain includes a simple linear layer (i.e., our target model) and unlabeled camouflaged objects. We then design a pipeline for foreground-background-contrastive selfadversarial domain adaptation, to achieve robust UCOS. As a result, our baseline model achieves superior segmentation performance when compared with competing unsupervised models on the UCOS benchmark, with the training set which's scale is only one tenth of the supervised COS counterpart. The UCOS benchmark and our baseline model are now publicly available(1).

关键词： Source Free Domain Adaptation unsupervised image segmentation

来源：评论

学校读者我要写书评

暂无评论

BCNN: Backpropagation CNN-Based fully unsupervised skull stripping for accurate brain segmentation

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 88卷

作者： Verma, Poonam Rani Bhandari, Ashish Kumar Natl Inst Technol Patna Dept Elect & Commun Engn Patna 800005 India

Brain skull stripping is an essential step before performing the segmentation. It leads to better performance and less computational load on the model due to the elimination of redundant features from the image. However, the preparation of the skull-stripped ground truth brain images by the experts is a very tedious task and may lead to human errors. In this article, a fully unsupervised approach to brain extraction has been proposed. The cascaded loss function is used and is tuned for better segmentation. The number of connected components is also tuned in each type of dataset. The cascaded loss function is a combination of focal loss (FL) and dice loss (DL). To address the class imbalance issue, the leaky ReLU activation function is used. Enhancement of the brain image has been performed before extraction which yielded better performance. In comparison with other methods, the proposed backpropagation-based convolutional neural network (BCNN) work gives better qualitative and quantitative outcomes on four out of seven parameters. The dice similarity coefficient (DSC) of the proposed model is 0.89 which is the highest as compared to the other models for brain extraction. The specificity of the model is 0.998 with 97.21 % accuracy. The undersegmentation error is reduced to 1.2002 using the cascaded loss function. The proposed work has been evaluated on four brain image datasets. It has been found that the proposed model extracts the brain from the skull and also the white matter, gray matter, and cerebrospinal fluid. Therefore, it has been noted that the proposed model will be beneficial for efficient brain skull stripping without the availability of ground truth data.

关键词： Brain extraction Brain tissues Focal loss Skull stripping unsupervised image segmentation

来源：评论

学校读者我要写书评

暂无评论

unsupervised Natural image segmentation via Bayesian Ying-Yang Harmony Learning Theory

引用

NEUROCOMPUTING 2013年 121卷 532-539页

作者： Zhu, Shaojun Zhao, Jieyu Guo, Lijun Zhang, Yuanyuan Ningbo Univ Inst Comp Sci & Technol Ningbo 315211 Zhejiang Peoples R China

An unsupervised image segmentation method for natural images is proposed in this paper. We assume that texture features in natural images are distributed as a mixture of Gaussians. In order to cluster the extracted feature vectors, we modify a clustering algorithm based on Bayesian Ying-Yang (BYY) harmony learning theory with Dirichlet-Normal-Wishart prior. This algorithm can determine the number of components automatically during the clustering procedure, as long as we give a large enough initial component number. Our works in this paper have presented a complete pipeline of clustering-based image segmentation including feature extraction, robust feature clustering and methodological effective post processing. The experiments reported in this paper demonstrate that the proposed method is efficient (in terms of visual evaluation and quantitative performance measures) and performs competitively compared to the existing state-of-the-art segmentation methods. (C) 2013 Elsevier B.V. All rights reserved.

关键词： unsupervised image segmentation Bayesian Ying-Yang harmony learning Dirichlet-Normal-Wishart prior Superpixels Automatic model selection

来源：评论

学校读者我要写书评

暂无评论

An In-situ Real-time Hidden Damage Inspection on C-17 Globemaster III Composite Aileron using LSP Technique under Thermal Excitation

An In-situ Real-time Hidden Damage Inspection on C-17 Globem...

引用

Conference on Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems

作者： Fong, Rey-Yie Yuan, Fuh-Gwo North Carolina State Univ Dept Mech & Aerosp Engn Smart Struct & Mat Lab Raleigh NC 27695 USA NIA Integrated Struct Hlth Management Lab Hampton VA 23666 USA

ISBN: (数字)9781510640122

ISBN: (纸本)9781510640122

A non-contact, full-field vision-based non-destructive inspection (V-NDI) system was developed with multiple damages detection capabilities in composite structures under thermal excitation. In contrast to point-based non-destructive inspection (P-NDI) systems employing laser Doppler vibrometer (LDV) with discrete wavefield captured by pointwise scanning, the V-NDI system captures higher spatial resolution wavefield by a CMOS camera for every time instance without repeating the experiment tens of thousand times to reassemble the wavefield like P-NDI. An Advanced Damage Processing Network (ADPNet) was proposed with laser speckle photometry (LSP) employed in a V-NDI system for hidden damages inspection. The LSP/ADPNet system relies on observing the variation of speckle clouds in time sequence without a baseline and is very insensitive to ambient noise with statistics based image processing where traditional holography/ESPI suffers greatly. Other advances of LSP/ADPNet system are its robust tolerance of laser coherence, larger illumination area, flexible choice of correlation functions, and more advanced post-processing techniques such as Bayesian updating/inference or unsupervised image segmentation that can be readily applied. Thermal excitation can have very large power throughput in hundreds of watts compared to traditional PZT actuator, merely in a few watt ranges. Laser speckle itself is the result of self-interference scatter field reflected from a rough surface, and each speckle can be treated as a sensing point from a randomly distributed speckle cloud. By observing the variation of speckle cloud on the structure surface, displacement related quantities in higher dimensions (e.g. hypercomplex envelope, phase between real-valued signal and its quadrature, phase congruency, etc.) can be deduced by the Riesz bp transform and correlated in time sequence to highlight the location of hidden damages in a very effective way. Another novelty of this paper is to make a s

关键词： BVID non-destructive inspection LSP ADPNet Riesz bp transform hypercomplex domain unsupervised image segmentation FPGA wavefield reconstruction DIC

来源：评论

学校读者我要写书评

暂无评论

unsupervised segmentation of multiview feature semantics by hashing model

引用

SIGNAL PROCESSING 2019年 160卷 106-112页

作者： Cui, Jia Zhao, Yanhui Dong, Xinfeng Tang, Mingxi Shandong Normal Univ Sch Informat Sci & Engn Jinan 250014 Shandong Peoples R China Shaanxi Fash Engn Univ Xian 712046 Shaanxi Peoples R China

The image segmentation of finely detailed object in images is becoming increasingly important in various image applications. Herein, multiview features such as color, spatial features, texture, saliency, and depth are used to calculate the feature semantic that differentiates the image foreground and background at the pixel level. For different image type, the importance of every single image feature is various. We assume that combining multiple features will produce improved results compared to using any single feature and propose an unsupervised learning strategy to learn optimal feature projection to the final solution surface of binary segmentation. To reduce computational complexity, a hashing model is used to represent the projected feature using binary codes, as its hamming distance efficiently retrieves the pixel similarity. Comparative experiments using the current state-of-the-art unsupervised segmentation algorithms and a deep learning approach, i.e., a fully convolutional network, demonstrate the advantages of the proposed method. (C) 2019 Published by Elsevier B.V.

关键词： unsupervised image segmentation Multiview feature projection Similarity distance Hashing model

来源：评论

学校读者我要写书评

暂无评论

unsupervised segmentation of natural images based on statistical modeling

引用

NEUROCOMPUTING 2017年 252卷 95-101页

作者： Zhu, Zhong-jie Wang, Yu-er Jiang, Gang-yi Zhejiang Wanli Univ Ningbo Key Lab DSP Ningbo 315100 Zhejiang Peoples R China Ningbo Univ Inst Circuits & Syst Ningbo 315211 Zhejiang Peoples R China

A novel unsupervised scheme for natural image segmentation is proposed aiming to acquire perceptually consistent results. Firstly, comprehensive visual features besides raw color values are extracted, including spatial frequency, contrast sensitivity, color deviation, and so on. Secondly, high correlations among visual features are reduced via principal component analysis (PCA) and the raw image pixels are then converted to a collection of feature vectors in a multi-dimensional feature space. Thirdly, the Gaussian mixture model (GMM) is employed to approximate the class distribution of image pixels and an improved, expectation maximization (EM) algorithm is introduced to estimate model parameters. Finally, segmentation results are obtained by grouping of pixels based on the mixture components. Experiments are conducted and the results demonstrate that, compared with existing techniques, the proposed scheme can acquire more perceptually consistent results. (C) 2017 Elsevier B.V. All rights reserved.

关键词： unsupervised image segmentation Visual feature PCA Statistical modeling Improved EM algorithm

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：