检索结果-内蒙古大学图书馆

Improved cross-media relevance model for automatic image annotation

ICIC Express Letters, Part B: Applications 2012年第5期3卷 1231-1237页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Bao, Cuizhu Liu, Yongkui Xu, Lu Institute of Computer Graphics and Image Processing Dalian Nationalities University No. 18 Liaohe Road Economic and Technological Development Zone-Dalian 116600 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University No. 2699 Qianjin Avenue Changchun 130012 China

Automatic image annotation has been an active research topic in the last decade due to its potentially large impact on image retrieval, object recognition and image understanding. Many approaches have been proposed for image annotation in recent years. The most influential annotation model is relevance model, whose representative algorithm is Cross-Media Relevance Model (CMRM). In this paper, to overcome the shortcomings of the original CMRM, we propose improved CMRM. In the improved CMRM, the annotation word distribution is estimated using binary probability, the significance of blob is discriminately depicted using TF-IDF (term frequency-inverse document frequency) schemes, and the similarity measurement of blob is based on blob and continuousvalued feature vector. The experimental results on the standard Corel5K dataset show that our proposed approach outperforms the original CMRM by about 111% and 73% in terms of F1 and N+ measures respectively. The improved CMRM can get better performance in specific domains such as cultural heritage and special necessities digitization for ethnic minorities. © 2012 ICIC International.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

image annotation refinement using dynamic weighted voting based on mutual information

Journal of Software

引用

Journal of Software 2011年第11 SPEC. ISSUE期6卷 2239-2246页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Institute of Computer Graphics and Image Processing Dalian Nationalities University Dalian China State Key Laboratory of CAD and CG Zhejiang University Hangzhou China

Automatic image annotation is a promising solution to narrow the semantic gap between low-level content and high-level semantic concept, which has been an active research area in the fields of image retrieval, pattern recognition, and machine learning. However, even the most dedicated annotation algorithms are often unsatisfactory. image annotation refinement has attracted much more attention recently. In this paper, a novel refinement algorithm using dynamic voting based on mutual information is proposed. Unlike the traditional refinement algorithm, the proposed algorithm adopts dynamic weighted voting to measure the dependence between the candidate annotations, which not only permits that the annotations with higher probabilities deny the annotations with lower probabilities, but also permits that the annotations with lower probabilities deny the annotations with higher probabilities. The proposed refinement algorithm adopts progressive method instead of iterative, which can significantly decrease the time cost of refining annotations. In order to further improve efficiency without sacrificing precision, we propose the block-based normalized cut algorithm to segment image. Experiments conducted on standard Washington Ground Truth image Database demonstrate the effectiveness and efficiency of our proposed approach for refining image annotations. © 2011 ACADEMY PUBLISHER.

关键词： image annotation

来源：评论

学校读者我要写书评

暂无评论

Content- and semantic-based progressive multimodal image retrieval

引用

ICIC Express Letters 2011年第1期5卷 201-206页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Zhang, Xiaoli Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Avenue Changchun 130012 China Institute of Computer Graphics and Image Processing Dalian Nationalities University Economic and Technological Development Zone Liaohe Road Dalian 116600 China

image retrieval has been an active research topic due to its great importance in the field of image management, digital library and web searching. However, the performances of the existing approaches, including text-based or content-based image retrieval, are often unsatisfactory. Inspired by text-based image retrieval, we propose semantic-based approach, whose similarity computation is semantic relevance rather than word matching. In this paper, a novel approach of progressive image retrieval based on content and semantic is proposed. The proposed retrieval model overcomes the drawbacks of pure content-based and text-based image retrieval, which exploits the strengths of both semantic- and content-based methods, minimizing their weaknesses. Experiments demonstrate the effectiveness and efficiency of the proposed method for image retrieval. © 2011 ISSN.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Interactive simulation and visualization of fluids with surface raycasting

Interactive simulation and visualization of fluids with surf...

引用

23rd SIBGRAPI Conference on graphics, Patterns and images, SIBGRAPI 2010

作者： Inácio, Renan Teston Nobrega, Tiago H. C. Carvalho, Diego D. B. Von Wangenheim, Aldo LAPIX - Laboratory for Image Processing and Computer Graphics Federal University of Santa Catarina Florianópolis Brazil

ISBN: (纸本)9780769542300

We present a method to couple particle-based fluid simulation methods such as Smoothed Particle Hydrodynamics (SPH) and volume rendering in order to visualize the fluid. A volume is generated from the fluid's implicit density field so volume raycasting can be performed to render the surface on the GPU. The volume generation algorithm is also implemented in the GPU and is suitable to be used with both SPH simulations implemented on CPU and GPU. We compare different implementations of fluid simulation, demonstrating the modularity of the volume generation method and concluding that it can be used together with other particle-based simulation models and other volume rendering techniques. © 2010 IEEE.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Degree elevation operator and geometric construction of C-B-spline curves

引用

Science China(Information Sciences) 2010年第9期53卷 1753-1764页

作者： ZHU Ping1,2*,WANG GuoZhao1 & YU JingJing1 1Institute of Computer graphics and image processing,Zhejiang University,Hangzhou 310027,China 2laboratory of Scientific Computing,Southeast University,Nanjing 211189,China 1. Institute of Computer Graphics and Image Processing Zhejiang University Hangzhou 310027 China2. Laboratory of Scientific Computing Southeast University Nanjing 211189 China

Unlike a B'ezier curve,a spline curve is hard to be obtained through geometric corner cutting on control polygons because the degree elevation operator is difficult to be obtained and geometric convergence is hard to be *** order to obtain geometric construction algorithm on C-B-splines,firstly we construct the degree elevation operator by using bi-order splines in this *** we can obtain a control polygon sequence by degree elevation based on the degree elevation operator derived from a C-B-spline ***,we prove that this polygon sequence will converge to initial C-B-spline *** geometric construction algorithm possesses strong geometric *** is also simple,stable and suitable for hardware to *** algorithm is important for CAD modeling systems,since many common engineering curves such as ellipse,helix,*** be represented explicitly by C-B-splines.

关键词： C-B-spline degree elevation operator bi-order C-B-spline geometric convergence geometric construction

来源：评论

学校读者我要写书评

暂无评论

Using acceleration data from smartphones to interact with 3D medical data

Using acceleration data from smartphones to interact with 3D...

引用

23rd SIBGRAPI Conference on graphics, Patterns and images, SIBGRAPI 2010

作者： De Souza, Mateus Carvalho, Diego Dias Bispo Barth, Peter Ramos, Jeferson Vieira Comunello, Eros Von Wangenheim, Aldo LAPIX - Laboratory for Image Processing and Computer Graphics Federal University of Santa Catarina Florianópolis Brazil Hochschule RheinMain Wiesbaden Germany

ISBN: (纸本)9780769542300

Accelerometers integrated in modern smartphones pave the way to intuitively use gestures for collaboratively controlling interactive applications. Using and holding smartphones has become natural and ensures user acceptance as well as intuitive handling. We focus on using accelerators in several smartphones at the same time to interactively control a medical imaging solution. To this end, we introduce a framework to collect, modify, and distribute acceleration sensor data from multiple smartphones and integrate it with a medical imaging system which results in an environment suitable for e.g. doctors reviewing and explaining diagnostic findings. We performed some experiments to evaluate the usability of this approach and present an ongoing research in adapting the smartphone interface to physical simulation applications. © 2010 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Extraction of human body skeleton based on silhouette images

Extraction of human body skeleton based on silhouette images

引用

2nd International Workshop on Education Technology and Computer Science, ETCS 2010

作者： Ding, Jianhao Wang, Yigang Yu, Lingyun State Key Laboratory of CAD and CG Zhejiang University Hangzhou China Institute of Computer Graphics and Image Processing Hangzhou Dianzi University Hangzhou China Department of Mathematics and Computing Science University of Groningen Netherlands

ISBN: (纸本)9780769539874

Skeleton extraction is essential for general shape representation. A typical skeletonization algorithm should obtain the ability to preserve original object's topological and hierarchical properties. However, most of current methods are high memory cost, computationally intensive, and also require complex data structures. In this paper, we propose an efficient and accurate skeletonization method for the skeleton feature points extracted from human body based on silhouette images. First, the gradient of distance transform is used to detect critical points inside the foreground. Then, we converge and simplify critical points in order to generate the most important and elegant skeleton feature points. Finally, we present an algorithm which connects the skeleton feature points and estimates the position of skeleton joints. © 2010 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Block-based normalized-cut algorithm for image segmentation

Block-based normalized-cut algorithm for image segmentation

引用

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Chen, Jingrun Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China Institute of Computer Graphics and Image Processing Dalian Nationalities University Dalian China State Key Laboratory of CAD and CG Zhejiang University Hangzhou China

ISBN: (纸本)9783642051722

Automatic image segmentation remains a challenging problem in the fields of computer vision, image analysis and understanding. A lot of algorithms and technologies have been proposed and developed for image segmentation, among which the N-cut has been a promising method and active research area due to better quality. But the N-cut can't process medium and large image dataset online due to incredible memory and time complexity. Moreover, the N-cut algorithm can't utilize texture information since its basic unit of clustering algorithm is pixel. To overcome the drawback and improve the description power, the paper proposes a block-based N-cut algorithm for image segmentation, whose basic unit of clustering is image block instead of individual pixel. Block-based algorithm not only decreases the time and storage complexity, but also improves the discrimination power of visual feature vector. The experiments demonstrate that proposed algorithm outperform the original N-cut algorithm in efficiency. Experiments show that the proposed block-based N-cut algorithm is more suitable for online processing large-scale data. © 2010 Springer-Verlag Berlin Heidelberg.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

An efficient and effective automatic image annotation using positive and negative example images

引用

ICIC Express Letters 2011年第8 B期5卷 2927-2932页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Bao, Cuizhu Dong, Yuying Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University No. 2699 Qianjin Avenue Changchun 130012 China Institute of Computer Graphics and Image Processing Dalian Nationalities University No. 18 Liaohe Road Eco. and Tech. Dev. Zone Dalian 116600 China College of Computer Science and Engineering Dalian Nationalities University No. 18 Liaohe Road Eco. and Tech. Dev. Zone Dalian 116600 China College of Life Science Dalian Nationalities University No. 18 Liaohe Road Eco. and Tech. Dev. Zone Dalian 116600 China

Automatic image annotation is an active topic and difficult task in computer vision domain, which has attracted more and more researchers' attention. Many approaches have been proposed to automatically annotate images. To improve the annotation quality, most of them have profound principlessophisticated modelsand high time complexities. How to efficiently annotate image is becoming one key issue in the field of computer vision. We propose a very efficient and effective approach called keyword vector classification approach, whose model is very simple. Experiments on Corel5K dataset show that the annotation performance of the our proposed approach is almost four times better than translation model and twice better than CMRM (in terms of precision, recall and F1) while the time cost of ours surprisingly decreases. In addition, to our knowledge, our proposed approach outperforms most of existing ones in terms of N+. © 2011 ISSN 1881-803X.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

Lossless Compression of Maps, Charts, and Graphs via Color Separation

Lossless Compression of Maps, Charts, and Graphs via Color S...

引用

Data Compression Conference (DCC)

作者： Saif alZahir Arber Borici Graphics and Image Processing Laboratory Computer Science University of Northern British Columbia BC Canada

ISBN: (纸本)9781424464258

Summary form only given. In this research, we present a fast and efficient lossless compression scheme for discrete-color digital map images, charts, and graphs stored in the raster image format. The proposed scheme determines the number of different colors in the given image and creates a separate bi-level data layer for each color. Then, the bi-level layers are individually compressed using the proposed algorithm. This scheme comprises two components: (i) a codebook; and (ii) our row-column reduction coding algorithm, RCRC. The codebook is a fixed-to-variable Huffman dictionary that is based on symbol entropy. The second component of our scheme is a new algorithm, the RCRC, designed to deal with those blocks that are not found in the codebook. Our experimental results show that our lossless compression scheme achieved an average compression equal to 0.035 bpp for map images and 0.03 bpp for charts and graphs. These results are better than most reported results in the literature. Moreover, our scheme is simple and fast.

关键词： image coding Frequency Data compression Color Computer graphics image processing Computer science Partitioning algorithms Dictionaries Entropy

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：