检索结果-内蒙古大学图书馆

Dinkelbach NCUT: An Efficient Framework for Solving Normalized Cuts Problems with Priors and Convex Constraints

INTERNATIONAL JOURNAL OF COMPUTER VISION 2010年第1期89卷 40-55页

作者： Ghanem, Bernard Ahuja, Narendra Univ Illinois Dept Elect & Comp Engn Beckman Inst Adv Sci & Technol Urbana IL 61801 USA

In this paper, we propose a novel framework, called Dinkelbach NCUT (DNCUT), which efficiently solves the normalized graph cut (NCUT) problem under general, convex constraints, as well as, under given priors on the nodes of the graph. Current NCUT methods use generalized eigen-decomposition, which poses computational issues especially for large graphs, and can only handle linear equality constraints. By using an augmented graph and the iterative Dinkelbach method for fractional programming (FP), we formulate the DNCUT framework to efficiently solve the NCUT problem under general convex constraints and given data priors. In this framework, the initial problem is converted into a sequence of simpler sub-problems (i.e. convex, quadratic programs (QP's) subject to convex constraints). The complexity of finding a global solution for each sub-problem depends on the complexity of the constraints, the convexity of the cost function, and the chosen initialization. However, we derive an initialization, which guarantees that each sub-problem is a convex QP that can be solved by available convex programming techniques. We apply this framework to the special case of linear constraints, where the solution is obtained by solving a sequence of sparse linear systems using the conjugate gradient method. We validate DNCUT by performing binary segmentation on real images both with and without linear/nonlinear constraints, as well as, multi-class segmentation. When possible, we compare DNCUT to other NCUT methods, in terms of segmentation performance and computational efficiency. Even though the new formulation is applied to the problem of spectral graph-based, low-level image segmentation, it can be directly applied to other applications (e.g. clustering).

关键词： Normalized graph cuts graph theory graph cuts Interactive segmentation graph-based image segmentation Dinkelbach method for fractional programming Quadratic programming Conjugate gradient method Eigen-decomposition Multi-way segmentation

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Detection via graph-based Ranking and segmentation Algorithms

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2015年第12期45卷 1509-1521页

作者： Yuan, Xue Guo, Jiaqi Hao, Xiaoli Chen, Houjin Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China

The majority of existing traffic sign detection systems utilize color or shape information, but the methods remain limited in regard to detecting and segmenting traffic signs from a complex background. In this paper, we propose a novel graph-based traffic sign detection approach that consists of a saliency measure stage, a graph-based ranking stage, and a multithreshold segmentation stage. Because the graph-based ranking algorithm with specified color and saliency combines the information of color, saliency, spatial, and contextual relationship of nodes, it is more discriminative and robust than the other systems in terms of handling various illumination conditions, shape rotations, and scale changes from traffic sign images. Furthermore, the proposed multithreshold segmentation algorithm focuses on all the nodes with a nonzero ranking score, which can effectively solve problems such as complex background, occlusion, various illumination conditions, and so on. The results for three public traffic sign sets show that our proposed approach leads to better performance than the current state-of-the-art methods. Moreover, the results are satisfactory even for images containing traffic signs that have been rotated or undergone occlusion, as well as for images that were photographed under different weather and illumination conditions.

关键词： graph-based image analysis graph-based image segmentation traffic sign detection

来源：评论

学校读者我要写书评

暂无评论

graph-based Horizon Line Detection for UAV Navigation

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2021年 14卷 11683-11698页

作者： Xu, Yong Yan, Hongtao Ma, Yue Guo, Pengyu Aerosp Technol Inst CARDC Mianyang 621000 Sichuan Peoples R China Acad Mil Natl Innovat Inst Def Technol Beijing 100071 Peoples R China

Perceiving the horizon line is a critical alternative for unmanned aerial vehicle (UAV) autonomous navigation, especially in the presence of noise-induced drift, unavailability of satellite navigation, and multipath errors. However, it's quite tough to detect the horizon line, due to the remotely sensed big data, the dynamic changes in flight, and the serious consequences of failure. To address these problems, we propose a graph-based horizon line detection technique that is composed of graph-based image segmentation, connected domain cascade filtering, horizon line extraction, and UAV attitude estimation. We improve the graph-based image segmentation algorithm so that the segmentation results are more conducive to horizon line detection. We then determine the sky-component by cascade filtering and extract the horizon line based on the boundaries of the sky-component. Furthermore, we directly compute the roll and pitch according to the extracted horizon line and eliminate the ambiguity of the angles. To validate our approach qualitatively and quantitatively, we designed a fixed-wing UAV system. We then validated our algorithm through extensive flights under various conditions and compared the estimated rolls and pitches to the IMU ones. Statistical results show that the proposed technique provides unbiased attitude angles with error variance of about 2(o), which verify the validity and robustness of our method. For engineering, our program runs at approximately 60 fps on the fly after optimizing.

关键词： Unmanned aerial vehicles image segmentation image edge detection Aircraft navigation Satellite navigation systems Task analysis Simultaneous localization and mapping Connected domain cascade filtering graph-based image segmentation horizon line detection unmanned aerial vehicle (UAV) navigation

来源：评论

学校读者我要写书评

暂无评论

No-reference image quality assessment using Prewitt magnitude based on convolutional neural networks

引用

SIGNAL image AND VIDEO PROCESSING 2016年第4期10卷 609-616页

作者： Li, Jie Zou, Lian Yan, Jia Deng, Dexiang Qu, Tao Xie, Guihui Wuhan Univ Sch Elect Informat Wuhan 430072 Hubei Peoples R China

No-reference image quality assessment is of great importance to numerous image processing applications, and various methods have been widely studied with promising results. These methods exploit handcrafted features in the transformation or space domain that are discriminated for image degradations. However, abundant a priori knowledge is required to extract these handcrafted features. The convolutional neural network (CNN) is recently introduced into the no-reference image quality assessment, which integrates feature learning and regression into one optimization process. Therefore, the network structure generates an effective model for estimating image quality. However, the image quality score obtained by the CNN is based on the mean of all of the image patch scores without considering the human visual system, such as edges and contour of images. In this paper, we combine the CNN and the Prewitt magnitude of segmented images and obtain the image quality score using the mean of all the products of the image patch scores and weights based on the result of segmented images. Experimental results on various image distortion types demonstrate that the proposed algorithm achieves good performance.

关键词： No-reference image quality assessment Convolutional neural networks (CNNs) graph-based image segmentation Prewitt magnitude

来源：评论

学校读者我要写书评

暂无评论

Head direction estimation from low resolution images with scene adaptation

引用

COMPUTER VISION AND image UNDERSTANDING 2013年第10期117卷 1502-1511页

作者： Chamveha, Isarun Sugano, Yusuke Sugimura, Daisuke Siriteerakul, Teera Okabe, Takahiro Sato, Yoichi Sugimoto, Akihiro Univ Tokyo Meguro Ku Tokyo 1538505 Japan Natl Inst Informat Chiyoda Ku Tokyo 1018430 Japan

This paper presents an appearance-based method for estimating head direction that automatically adapts to individual scenes. Appearance-based estimation methods usually require a ground-truth dataset taken from a scene that is similar to test video sequences. However, it is almost impossible to acquire many manually labeled head images for each scene. We introduce an approach that automatically aggregates labeled head images by inferring head direction labels from walking direction. Furthermore, in order to deal with large variations that occur in head appearance even within the same scene, we introduce an approach that segments a scene into multiple regions according to the similarity of head appearances. Experimental results demonstrate that our proposed method achieved higher accuracy in head direction estimation than conventional approaches that use a scene-independent generic dataset. (C) 2013 Elsevier Inc. All rights reserved.

关键词： Head direction estimation Low resolution image Appearance-based approach Scene adaptation graph-based image segmentation Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Interactive Multi-object segmentation in Medical images 15th

Efficient Interactive Multi-object Segmentation in Medical I...

引用

15th European Conference on Computer Vision (ECCV)

作者： Castaneda Leon, Leissi Margarita Vechiatto de Miranda, Paulo Andre Univ Sao Paulo Inst Math & Stat Sao Paulo Brazil

ISBN: (纸本)9783030110185;9783030110178

In medical image segmentation, it is common to have several complex objects that are difficult to detect with simple models without user interaction. Hence, interactive graph-based methods are commonly used in this task, where the image is modeled as a connected graph, since graphs can naturally represent the objects and their relationships. In this work, we propose an efficient method for the multiple object segmentation of medical images. For each object, the method constructs an associated weighted digraph of superpixels, attending its individual high-level priors. Then, all individual digraphs are integrated into a hierarchical graph, considering structural relations of inclusion and exclusion. Finally, a single energy optimization is performed in the hierarchical weighted digraph satisfying all the constraints and leading to globally optimal results. The experimental evaluation on 2D medical images indicates promising results comparable to the state-of-the-art methods, with low computational complexity.

关键词： Medical image segmentation Interactive segmentation graph-based image segmentation Superpixels segmentation

来源：评论

学校读者我要写书评

暂无评论

Method for selection macular edema region using optical coherence tomography data

COMPUTER OPTICS

引用

COMPUTER OPTICS 2020年第2期44卷 250-+页

作者： Ilyasova, N. Yu Demin, N. S. Shirokanev, A. S. Kupriyanov, A., V Zamytskiy, E. A. Samara Natl Res Univ Moskovskoye Shosse 34 Samara 443086 Russia IPSI RAS Molodogvardeyskaya 151 Samara 443001 Russia Samara Reg Clin Ophthalmol Hosp Samara Russia

The paper proposes a method for selection the region of diabetic macular edema in fundus images using OCT data. The relevance of the work is due to the need to create support systems for laser coagulation to increase its effectiveness. The proposed algorithm is based on a set of image segmentation methods, as well as searching for specific points and compiling their descriptors. The Canny method is used to find the boundary between the vitreous body and the retina in OCT images. The segmentation method, based on the Kruskal algorithm for constructing the minimum spanning tree of a weighted connected undirected graph, is used to select the retina to the pigment layer in the image. Using the results of segmentation, a map of the thickness of the retina of the eye and its deviation from the norm were constructed. In the course of the research, the optimal parameter values were selected in the Canny and graph segmentation algorithms, which allow to achieve a segmentation error of 5 %. SIFT, SURF, and AKAZE methods were considered for superimposing calculated maps of the retina thickness and its deviation from the norm on the fundus image. In cases where a picture from the fundus camera of the OCT apparatus is provided along with OCT data, using the SURF method, it is possible to accurately combine with the fundus image.

关键词： laser coagulation eye fundus diabetic retinopathy OCT images graph-based image segmentation SIFT SURF descriptors

来源：评论

学校读者我要写书评

暂无评论

Salient Region Detection based on SLIC and graph-based segmentation

Salient Region Detection Based on SLIC and Graph-based Segme...

引用

2016 4th International Conference on Advanced Materials and Information Technology Processing(AMITP 2016)

作者： Xiaofei Sun Wenwen Pan Xia Wang Xuhong Li Guan Wang College of Information Science and Engineering Zaozhuang University

At present, the most recent saliency detection algorithms are still not satisfactory. A saliency detection algorithm based on SLIC and graph-based segmentation is proposed. Firstly, graph-based segmentation is used to obtain larger image partitions, and the partitions with good contours are acquired. Then the relatively detailed partitions are obtained using SLIC image segmentation. Sparse color histogram is applied to these two methods. By using the color and spatial distance information, the saliency of each partition is calculated. Contours of salient objects from saliency maps generated using graph-based segmentation are acquired and the gray scale values of the two kinds of saliency maps in the area surrounded by contours are merged. Experimental results show that compared with other detection methods, the proposed algorithm can effectively detect the salient object in the image.

关键词： saliency map graph-based image segmentation SLIC color sparse histogram

来源：评论

学校读者我要写书评

暂无评论

基于颜色和纹理的图像检索研究与实现

基于颜色和纹理的图像检索研究与实现

引用

作者：王永安电子科技大学

学位级别：硕士

在现在这个数字化、信息化的社会里,随着多媒体技术、互联网技术的迅猛发展、存储设备容量的剧增和存储代价的减少,各种数字化产品如数码照相机、数码摄像机等的出现和广泛普及,导致信息量的急剧增长,尤其是图像和音视频等多媒体数据。... 详细信息

在现在这个数字化、信息化的社会里,随着多媒体技术、互联网技术的迅猛发展、存储设备容量的剧增和存储代价的减少,各种数字化产品如数码照相机、数码摄像机等的出现和广泛普及,导致信息量的急剧增长,尤其是图像和音视频等多媒体数据。鉴于图像的重要作用和人们对效率、准确率的更高要求,这使得用计算机进行图像检索成为了一个在现实应用和科研理论上都有重大价值的研究课题。基于内容的图像检索(CBIR Content-based image Retrieval)技术正是这一研究课题的核心。基于内容的图像检索系统通过计算机完成图像的特征自动提取,并基于图像特征向量进行相似度计算,以此检索出相似图像。近年来,该技术已成为信息检索和图像处理等领域的热点研究方向。本文主要围绕CBIR中的一些关键技术进行了阐述和研究,研究重点是用于描述图像内容的图像特征的提取。系统探讨和分析了图像颜色特征的提取、图像纹理特征的提取、graph-based图像分割技术。本文的研究内容是图像检索领域的研究重心,在理论和现实应用中都具有重大的意义。本文的主要工作如下: 1、简单介绍了CBIR系统的框架并系统探讨和研究了其所使用的一些关键技术,主要包括图像颜色空间的表示与转换、图像颜色特征和纹理特征的提取、graph-based图像分割技术、基于特征向量的相似性度量以及检索效果的评价准则。并对基于颜色和纹理各个特征的检索效果进行了简单的测试。 2、提出了一种在图像分割基础上提取颜色和纹理特征来描述图像的方法。此算法先完成基于图的图像分割,然后对分割后的图像使用本文所述的颜色和纹理特征提取算法,提取颜色和纹理特征。该方法能提取出图像主体对象,减弱图片背景对图像特征的干扰,提高检索的速度和效果。 3、在Windows系统和Netbeans开发环境下,设计并开发实现了一个简易的CBIR系统。该系统实现了提取图像颜色特征和纹理特征的各个算法以及graph-based图像分割,可以完成基于颜色和纹理的图像检索。使用该系统,用户可以上传一幅待检索图片,并可以选择根据颜色特征,纹理特征或者组合特征进行检索,系统返回从图像库中检索出的相关图片。

关键词：基于内容的图像检索(CBIR) 特征提取 graph-based 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：