检索结果-内蒙古大学图书馆

Conference on Optoelectronic Imaging and Multimedia Technology

作者： Zhang, Hao He, Jin Zhang, Hong Huang, Zhanhua Tianjin Univ Coll Precis Instrument & Optoelect Engn Tianjin 300072 Peoples R China Tianjin Univ Technol & Educ Dept Elect Engn Tianjin Peoples R China Univ Alberta Dept Comp Sci Edmonton T6G 2E8 AB Canada

ISBN: (纸本)9780819483805

This paper proposed an interactive image segmentation algorithm that can tolerate slightly incorrect user constraints. interactive image segmentation was formulated as a constrained spectral graph partitioning problem. Furthermore, it was proven to equal to a supervised classification problem, where the feature space was formed by rows of the eigenvector matrix that was computed by spectral graph analysis. nu-SVM (support vector machine) was preferred as the classifier. Some incorrect labels in user constraints were tolerated by being identified as margin errors in nu-SVM. Comparison with other algorithms on real color images was reported.

关键词： interactive image segmentation incorrect user constraints constrained spectral graph partitioning supervised classification nu-SVM

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation Using Multimodal Regularized Kernel Embedding 17

Interactive Image Segmentation Using Multimodal Regularized ...

引用

17th IEEE International Conference on Machine Learning and Applications (IEEE ICMLA)

作者： Madani, El Moatasem Torki, Marwan Alexandria Univ Comp & Syst Engn Alexandria Egypt

ISBN: (纸本)9781538668054

interactive image segmentation is a classification problem that involves feature extraction like color features. However, in most cases the color features alone cannot discriminate foreground and background. This is due to the fact that both foreground and background can have possibly overlapping color modalities. Using kernels, different notions of pixel similarities can be incorporated. In this paper, we present an interactive image segmentation approach based on kernel embedding using Kernel Local Fisher Discriminant Analysis (KLFDA). We use KLFDA to transform pixel features into a new discriminative feature space. In this feature space the between-class separability is maximized and the locality within each class is preserved. One difficulty for using KLFDA is the setting for the regularization parameter epsilon. We propose different strategies to overcome this limitation. Our proposed strategies achieve better qualitative and quantitative results compared to state-of-the-art algorithms on the well known ISEG data set for interactive image segmentation.

关键词： interactive image segmentation KLFDA Kernels Regularization Bayesian Optimization

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation VIA MULTI-CUE DYNAMIC INTEGRATION

INTERACTIVE IMAGE SEGMENTATION VIA MULTI-CUE DYNAMIC INTEGRA...

引用

15th IEEE International Conference on image Processing (ICIP 2008)

作者： Zhao, Jieyu Geng, Xiaowei Ningbo Univ Res Inst Comp Sci & Technol Ningbo 315211 Zhejiang Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100084 Peoples R China

ISBN: (纸本)9781424417650

Due to the complex scenes involved in the natural images, some interactions with the user are necessary to obtain meaningful segmentation results. interactive image segmentation is such a processing technique which extracts objects from a complex image background according to the user's demand. There are many intrinsic attributes affecting the result of segmentation. It is hard to produce a good result based on a single clue of the image. This paper presents a novel image segmentation method based on the dynamic multi-cue integration. This method fuses color, texture, spatial and edge information via a conditional random field. Most existing image segmentation algorithms combine multiple cues statically with a constant ratio, it is hard for them to describe the inherent property of different images efficiently. The proposed method takes the full advantage of the user labeled information, and constructs a conditional random field containing different energy terms. These energy terms are fused dynamically in accordance with the image inner property, thus greatly improves the segmentation power of the model. In addition, we use the Jensen-Shannon divergence to extract the border information, which is robust against noise. The experimental results show the proposed method performs steady and works well on various natural images.

关键词： interactive image segmentation Conditional Random Fields Dynamic Integration Graph Cut

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation by Dynamic Region Merging

Interactive Image segmentation by Dynamic Region Merging

引用

International Conference on Data Mining and Intelligent Computing (ICDMIC)

作者： Banu, Sameena Giduturi, Apparao Sattar, Syed Abdul Khaja Banda Nawaz Coll Engn Dept CSE Gulbarga Karnataka India Gitam Univ Dept CSE Vishakhapatnam Andhra Pradesh India Royal Inst Technol Dept E&CE Hyderabad Andhra Pradesh India

ISBN: (纸本)9781479946747

In this paper dynamic region merging algorithm is proposed for interactive image segmentation. A part of image of user's interest is extracted from the input image and then segmentation is performed. This can be done by iteratively merging the regions according to some criteria. There are two issues in region merging algorithm: order of merging and stopping condition. In the proposed algorithm, the Sequential Probablity Ratio Test (SPRT) and minimal cost criterion are used to solve these two issues. The color image is converted to grayscale image and regions are merged if there is a proof for merging according to this predicate. The principle of dynamic programming is used to indicate the merging order. Experiments on different images are conducted to demonstrate the performance of the proposed dynamic region merging algorithm for interactive segmentation.

关键词： interactive image segmentation Region merging Wald's SPRT Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation by improved maximal similarity based region merging

Interactive image segmentation by improved maximal similarit...

引用

IEEE International Conference on Medical Imaging Physics and Engineering (ICMIPE)

作者： Jian, Chen Bin, Yan Hua, Jiang Lei, Zeng Li, Tong Natl Digital Switching Syst Engn & Technol R&D Ct Zhengzhou 450002 Peoples R China

ISBN: (纸本)9781467358873

In medical image processing, interactive image segmentation is an important part, because it can obtain accurate segment results with less human effort compared with manual scribing. We proposed an improved algorithm of maximal similarity based region merging, compared with the algorithm proposed in [3], our algorithm use SLIC superpixels segmentation to obtain presegmented regions, using SLIC superpixles, it is easy to control the number of presegmentation regions. We also introduce the texture features differeces while rigion merging, so we can obtain the accuracy of similarity measurement. Experimental results show that our algorithm can obtain comparable results.

关键词： interactive image segmentation Superpixels image merging

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation by Semi-supervised Learning Ensemble

Interactive Image Segmentation by Semi-supervised Learning E...

引用

International Symposium on Knowledge Acquisition and Modeling

作者： Xu, Jiazhen Chen, Xinmeng Huang, Xuejuan Wuhan Univ Comp Sch Wuhan 430072 Hubei Peoples R China

ISBN: (纸本)9780769534886

Due to the instinct difficulties of fully automatic segmentation, interactive image segmentation becomes a hot research topic in the past several years, and many approaches have been proposed Recently, an approach viewing this task as a semi-supervised learning problem shows great promising. However, this apporach ignores the influence of potential noise mingled in the user-privided information. Considering this information is mostly given by hand with the help of broad brush or region selection tools, the noise is inevitable. In this paper, We propose a more robust solution against noise by adopting Laplacian SVM method We also develop an ensemble method to increase the performance. Experiment results demonstrate the improvement over the former approaches.

关键词： SVM ensemble interactive image segmentation semi-supervised Learning

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation Using Elastic Interpolation 17

Interactive Image Segmentation Using Elastic Interpolation

引用

IEEE International Symposium on Multimedia (ISM)

作者： Meena, Sachin Palaniappan, Kannappan Seetharaman, Guna Univ Missouri Dept Comp Sci Columbia MO 65211 USA US Naval Res Lab Washington DC 20375 USA

ISBN: (纸本)9781509003792

Elastic body splines (EBS) belong to a family of splines introduced for biomedical image registration. EBS models the elastic deformation of a homogeneous isotropic elastic body subjected to external forces. The task of interactive image segmentation is framed as a semi-supervised interpolation where the basis functions are learned using the user provided seed points to model and predict the labels for the unlabeled pixels. Seed points are sparse compared to other methods that may require scribbles and regions. The spline for interpolating labels is the EBS which we compare to our previous work using Gaussian Elastic Body splines (GEBS) [1] for the task of interactive image segmentation. Experimental results show that the EBS is about 14 percent better, in terms of accuracy, than GEBS and significantly better than random walk and graph cut based segmentation. EBS is also 2.5 times faster than GEBS.

关键词： interactive image segmentation semi supervised regression elastic body splines

来源：评论

学校读者我要写书评

暂无评论

A survey of recent interactive image segmentation methods

引用

Computational Visual Media 2020年第4期6卷 355-384页

作者： Hiba Ramadan Chaymae Lachqar Hamid Tairi Department of Informatics Faculty of Sciences Dhar El MahrazUniversity of Sidi Mohamed Ben AbdellahFez 30000Morocco Faculty of Medicine and Pharmacy University of Sidi Mohamed Ben AbdellahFez 30000Morocco

image segmentation is one of the most basic tasks in computer vision and remains an initial step of many applications. In this paper, we focus on interactive image segmentation(IIS), often referred to as foreground–background separation or object extraction, guided by user interaction. We provide an overview of the IIS literature by covering more than 150 publications, especially recent works that have not been surveyed before. Moreover, we try to give a comprehensive classification of them according to different viewpoints and present a general and concise comparison of the most recent published works. Furthermore, we survey widely used datasets,evaluation metrics, and available resources in the field of IIS.

关键词： interactive image segmentation user interaction label propagation deep learning superpixels

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation with a regression based ensemble learning paradigm

引用

Frontiers of Information Technology & Electronic Engineering 2017年第7期18卷 1002-1020页

作者： Jin ZHANG Zhao-hui TANG Wei-hua GUI Qing CHEN Jin-ping LIU School of Information Science and Engineering Central South University Changsha 410083 China College of Computer and Communication Hunan University of Technology Zhuzhou 412007 China College of Mathematics and Computer Science Hunan Normal University Changsha 410083 China

To achieve fine segmentation of complex natural images, people often resort to an interactive segmentation paradigm, since fully automatic methods often fail to obtain a result consistent with the ground truth. However, when the foreground and background share some similar areas in color, the fine segmentation result of conventional interactive methods usually relies on the increase o f manual labels. This paper presents a novel interactive image segmentation method via a regression-based ensemble model with semi-supervised learning. The task is formulated as a non-linear problem integrating two complementary spline regressors and strengthening the robustness of each regressor via semi-supervised learning. First, two spline regressors with a complementary nature are constructed based on multivariate adaptive regression splines （MARS） and smooth thin plate spline regression （TPSR）. Then, a regressor boosting method based on a clustering hypothesis and semi-supervised learning is proposed to assist the training of MARS and TPSR by using the region segmentation information contained in unlabeled pixels. Next, a support vector regression （SVR） based decision fusion model is adopted to integrate the results of MARS and TPSR. Finally, the GraphCut is introduced and combined with the SVR ensemble results to achieve image segmentation. Extensive experimental results on benchmark datasets of BSDS500 and Pascal VOC have demonstrated the effectiveness of our method, and the com- parison with experiment results has validated that the proposed method is comparable with the state-of-the-art methods for in- teractive natural image segmentation.

关键词： interactive image segmentation Multivariate adaptive regression splines (MARS) Ensemble learning Thin-platespline regression (TPSR) Semi-supervised learning Support vector regression (SVR)

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation using region-based fully connected CRF models with graph cut based fine tuning

Interactive image segmentation using region-based fully conn...

引用

4th IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)

作者： Wang Dan Hu Guoqing Lyu Chengzhi South China Univ Technol Sch Mech & Automot Engn Guangzhou Peoples R China

ISBN: (数字)9781728143903

ISBN: (纸本)9781728143903

interactive image segmentation has gained much popularity since it can enhance the segmentation performance with human interactions. In this paper, we propose a novel framework that can effectively estimate the binary labels based on Conditional Random Field (CRF) models combining region-level information with pixels-level information. The user scribbles are treated as soft constraints. We use pixel-layer with local CRF and region-layer with fully connected CRF to model the graph. Then we combine the pixel information and region information together to calculate the pixels' likelihood term. In contrast to using relations between the pixel-layer and the region-layer during the probability computation, we calculate the probabilities of pixels and regions separately to reduce computational complexity. After the likelihood computation, a graph cut based model is used to refine the pixel-level label predictions of the image in order to avoid label inconsistency in regions and capture the boundary details. Due to the less relationship between layers and utilizing the refinement, the proposed model can provide high accuracy and user inputs insensitive results. Our experiments show that the proposed approach can efficiently and accurately segment the images compared with other state of art methods with only a few scribbles. Graph cut based fine tuning improves our segmentation accuracy and our method needs less computational cost than traditional multi-layer-based methods.

关键词： interactive image segmentation region-based model fully connected CRF graph cut

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：