检索结果-内蒙古大学图书馆

24th IEEE International Conference on image Processing (ICIP)

作者： Yu, Hongkai Zhou, Youjie Qian, Hui Xian, Min Wang, Song Univ South Carolina Columbia SC 29208 USA Zhejiang Univ Hangzhou Zhejiang Peoples R China Utah State Univ Logan UT 84322 USA

ISBN: (纸本)9781509021758

One popular approach to interactively segment an object of interest from an image is to annotate a bounding box that covers the object, followed by a binary labeling. However, the existing algorithms for such interactive image segmentation prefer a bounding box that tightly encloses the object. This increases the annotation burden, and prevents these algorithms from utilizing automatically detected bounding boxes. In this paper, we develop a new LooseCut algorithm that can handle cases where the bounding box only loosely covers the object. We propose a new Markov Random Fields (MRF) model for segmentation with loosely bounded boxes, including an additional energy term to encourage consistent labeling of similar appearance pixels and a global similarity constraint to better distinguish the foreground and background. This MRF model is then solved by an iterated max-flow algorithm. We evaluate LooseCut in three public image datasets, and show its better performance against several state-of-the-art methods when increasing the bounding-box size.

关键词： interactive image segmentation Graph cut Loosely bounded box

来源：评论

学校读者我要写书评

暂无评论

An Improved Random Walk Algorithm for interactive image segmentation 24th

An Improved Random Walk Algorithm for Interactive Image Segm...

引用

24th International Conference on Neural Information Processing (ICONIP)

作者： Wang, Peitao He, Zhaoshui Huang, Shifeng Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China Guangdong Univ Technol Inst Intelligent Signal Proc Guangzhou 510006 Peoples R China

ISBN: (纸本)9783319700908;9783319700892

interactive image segmentation is an important issue in computer vision. Many algorithms have been proposed for this problem. Among them, random walk based algorithms have been proved to be efficient. However, a large number of seeds (i.e., pixels with user-specified labels) must be given in advance to achieve a desirable segmentation for such algorithms, which makes user interaction inconvenient. To solve this problem, we improve the random walk algorithm in two aspects: (1) label prior is taken into account when computing edge weights between adjacent pixels;(2) each unseeded pixel is assigned with the same label as the seed with maximum first arrival probability to reduce the bias effect of seed size. The improved algorithm can achieve a desirable segmentation with few seeds. Experiment results on natural images illustrate the accuracy of the proposed algorithm.

关键词： interactive image segmentation Random walks Label prior

来源：评论

学校读者我要写书评

暂无评论

Graph-cut based interactive image segmentation with randomized texton searching

引用

COMPUTER ANIMATION AND VIRTUAL WORLDS 2016年第5期27卷 454-465页

作者： Ma, Wei Zhang, Yu Yang, Luwei Duan, Lijuan Beijing Univ Technol Coll Comp Sci Beijing Peoples R China

In the paper, we present an interactive image-segmentation method in the framework of graph cut, which incorporates not only traditional color and gradient constraints, but also a new type of texture constraint. Given an image with user-input strokes, we first establish the color and texture prior models of the foreground/background. The texture prior model, which is key to establish the texture constraints, is represented by local binary patterns (LBP) histograms. Then, an energy function composed of color, gradient, and texture terms is formulated. At last, by using graph cut, we minimize the energy function to obtain the foreground. In the energy function, the color and gradient terms have similar forms with traditional methods. The texture term in the function is generated using a proposed randomized texton-searching algorithm. First, the algorithm locates an approximately best representative texton for every unknown pixel as foreground and an approximately best one as background, through randomized searching. Second, it computes the LBP histograms of the two textons as the pixel's foreground/background texture descriptors, respectively. Finally, the distances between the descriptors and the foreground/background prior models are used to formulate the texture term. Experimental results demonstrate that our method outperforms traditional ones. Copyright (C) 2015 John Wiley & Sons, Ltd.

关键词： interactive image segmentation graph cut texture constraint LBP randomized texton searching

来源：评论

学校读者我要写书评

暂无评论

Fast interactive image segmentation Using Bipartite Graph Based Random Walk with Restart 7th

Fast Interactive Image Segmentation Using Bipartite Graph Ba...

引用

7th Pacific-Rim Symposium on image and Video Technology (PSIVT)

作者： Du, Yunfan Li, Fei Liu, Rujie Fujitsu Res & Dev Ctr Co Ltd Beijing Peoples R China

ISBN: (纸本)9783319294513;9783319294506

Although random walk with restart(RWR) has been successfully used in interactive image segmentation, the traditional implementation of RWR does not scale for large images. As the images are usually stored on local disk prior to user interaction, we can preprocess the images to save user time. In this paper, we do an offline precomputation that over-segments the input image into superpixels with different scales and then aggregates superpixels and pixels into one bipartite graph which fuses the high level and low level information. Given user scribbles, we do a realtime RWR on the bipartite graph by applying an approximate method which maps the RWR from pixel level to superpixel level. As the number of superpixels is far more less than the number of pixels in the image, our method reduces the amount of user time significantly. The experimental results demonstrate that our method achieves a similar result compared to original RWR along with outperforming in speed.

关键词： interactive image segmentation Random walk with restart Superpixel Bipartite graph

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation VIA CASCADED METRIC LEARNING

INTERACTIVE IMAGE SEGMENTATION VIA CASCADED METRIC LEARNING

引用

IEEE International Conference on image Processing (ICIP)

作者： Li, Wenbin Shi, Yinghuan Yang, Wanqi Wang, Hao Gao, Yang Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Collaborat Innovat Ctr Novel Software Technol & I Nanjing Peoples R China

ISBN: (纸本)9781479983391

In this paper, we propose an interactive image segmentation method from a novel perspective of cascaded metric learning. Given an image with user-marked scribbles that are essentially uncertain and noisy, our method completes the segmentation task by solving a binary classification problem. Starting from the initial training samples with known class labels (i.e., regions of the image that are believed with high confidence to be foreground or background), we first find an optimal metric that can best describe the classification of these samples. After that, we classify the unlabeled samples using the learnt metric. Samples classified with high confidence are used as new training samples to refine the metric. This cycle of metric learning and classification repeats until the accomplishment of the image segmentation task. The proposed method is extensively evaluated on the MSRC image set. Experiment results show that our method outperforms the state-of-the-art methods.

关键词： Cascaded Metric Learning interactive image segmentation Sample Selection

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation of Non-contiguous Classes Using Particle Competition and Cooperation 15th

Interactive Image Segmentation of Non-contiguous Classes Usi...

引用

15th International Conference on Computational Science and Its Applications (ICCSA)

作者： Breve, Fabricio Quiles, Marcos G. Zhao, Liang Sao Paulo State Univ UNESP Rio Claro SP Brazil Fed Univ Sao Paulo Unifesp Rio Claro SP Brazil Univ Sao Paulo Rio Claro SP Brazil

ISBN: (纸本)9783319214047;9783319214030

Semi-supervised learning methods employ both labeled and unlabeled data in their training process. Therefore, they are commonly applied to interactive image processing tasks, where a human specialist may label a few pixels from the image and the algorithm would automatically propagate them to the remaining pixels, classifying the entire image. The particle competition and cooperation model is a recently proposed graph-based model, which was developed to perform semi-supervised classification. It employs teams of particles walking in a undirected and unweighed graph in order to classify data items corresponding to graph nodes. Each team represents a class problem, they try to dominate the unlabeled nodes in their neighborhood, at the same time that they try to avoid invasion from other teams. In this paper, the particle competition and cooperation model is applied to the task of interactive image segmentation. image pixels are converted to graph nodes. Nodes are connected if they represent pixels with visual similarities. Labeled pixels generate particles that propagate their labels to the unlabeled pixels. Computer simulations are performed on some real-world images to show the effectiveness of the proposed approach. images are correctly segmented in regions of interest, including non-contiguous regions.

关键词： Semi-supervised learning interactive image segmentation Machine learning Particle competition and cooperation

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation Framework Based On Control Theory

Interactive Image Segmentation Framework Based On Control Th...

引用

Conference on Medical Imaging - image Processing

作者： Zhu, Liangjia Kolesov, Ivan Ratner, Vadim Karasev, Peter Tannenbaum, Allen SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA SUNY Stony Brook Dept Appl Math Stony Brook NY 11794 USA Atlanta Agilent Technol Atalanta GA USA

ISBN: (纸本)9781628415032

segmentation of anatomical structures in medical imagery is a key step in a variety of clinical applications. Designing a generic, automated method that works for various structures and imaging modalities is a daunting task. Instead of proposing a new specific segmentation algorithm, in this paper, we present a general design principle on how to integrate user interactions from the perspective of control theory. In this formulation, Lyapunov stability analysis is employed to design an interactive segmentation system. The effectiveness and robustness of the proposed method are demonstrated.

关键词： interactive image segmentation Control Theory Lyapunov Stability Active Contours

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

interactive Multilabel image segmentation via Robust Multilayer Graph Constraints

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2016年第12期18卷 2358-2371页

作者： Wang, Tao Ji, Zexuan Sun, Quansen Chen, Qiang Jing, Xiao-Yuan Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Sch Automat Nanjing 210094 Jiangsu Peoples R China

The combination of pixel and superpixel has been widely utilized in the interactive segmentation methods to overcome the sensitivity to the seeds' quantity and quality. However, because of the introduction of more variables and variables' interactions, the pixel-superpixel combination methods are still limited to the segmentation accuracy and computational complexity. To solve these problems, in this paper, we propose an interactive multilabel image segmentation method. In the proposed segmentation model, the multilayer relationships among the pixel layer, superpixel layer, and label layer are fused by the Markov random field framework to further improve the segmentation accuracy. During the optimization stage, the parallel partial optimality strategy is utilized to effectively solve the multilabel submodular energy function. Experimental results on challenging data sets demonstrate the competitiveness of the proposed method comparing with several state-of-the-art interactive algorithms.

关键词： interactive image segmentation multilabel Markov random field (MRF) multilayer graph graph cuts parallel partial optimality

来源：评论

学校读者我要写书评

暂无评论

Robust interactive image segmentation via graph-based manifold ranking

引用

Computational Visual Media 2015年第3期1卷 183-195页

作者： Hong Li Wen Wu Enhua Wu Department of Computer and Information Science University of Macao Chinese Academy of Sciences

interactive image segmentation aims at classifying the image pixels into foreground and background classes given some foreground and background markers. In this paper, we propose a novel framework for interactive image segmentation that builds upon graph-based manifold ranking model, a graph-based semi-supervised learning technique which can learn very smooth functions with respect to the intrinsic structure revealed by the input data. The final segmentation results are improved by overcoming two core problems of graph construction in traditional models: graph structure and graph edge weights. The user provided scribbles are treated as the must-link and must-not-link constraints. Then we model the graph as an approximatively k-regular sparse graph by integrating these constraints and our extended neighboring spatial relationships into graph structure modeling. The content and labels driven locally adaptive kernel parameter is proposed to tackle the insufficiency of previous models which usually employ a unified kernel parameter. After the graph construction,a novel three-stage strategy is proposed to get the final segmentation results. Due to the sparsity and extended neighboring relationships of our constructed graph and usage of superpixels, our model can provide nearly real-time, user scribble insensitive segmentations which are two core demands in interactive image segmentation. Last but not least, our framework is very easy to be extended to multi-label segmentation,and for some less complicated scenarios, it can even get the segmented object through single line interaction. Experimental results and comparisons with other state-of-the-art methods demonstrate that our framework can efficiently and accurately extract foreground objects from background.

关键词： interactive image segmentation graph structure graph edge weights manifold ranking relevance inference

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：