检索结果-内蒙古大学图书馆

Two-dimensional entropy model for video shot partitioning

Science in China(Series F) 2009年第2期52卷 183-194页

作者： ZHU SongHao LIU YunCai Institute of Image Process and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China

A shot presents a contiguous action recorded by an uninterrupted camera operation and frames within a shot keep spatio-temporal coherence. Segmenting a serial video stream file into meaningful shots is the first pass for the task of video analysis, content-based video understanding. In this paper, a novel scheme based on improved two-dimensional entropy is proposed to complete the partition of video shots. Firstly, shot transition candidates are detected using a two-pass algorithm： a coarse searching pass and a fine searching pass. Secondly, with the character of two-dimensional entropy of the image, correctly detected transition candidates are further classified into different transition types whereas those falsely detected shot breaks are distinguished and removed. Finally, the boundary of gradual transition can be precisely located by merging the characters of two-dimensional entropy of the image into the gradual transition. A large number of video sequences are used to test our system performance and promising results are obtained.

关键词： video shot segmentation two-dimensional entropy model coarse-to-fine algorithm content-based indexing and retrieval

来源：评论

学校读者我要写书评

暂无评论

A SYNTHESIS PROCEDURE FOR A GENERALIZEDNEURALNETWORK

A SYNTHESIS PROCEDURE FOR A GENERALIZEDNEURALNETWORK

引用

1992 International Joint Conference on Neural Networks, IJCNN 1992

作者： Yan, Yan Li, Jie Gu Institute of Image Process and Pattern Recognition Shanghai Jiao Tong University Shanghai200030 China

ISBN: (纸本)0780305590

A FTTB(From Top To Bottom) design strategy for neural network is introduced. From the scheme we present a design method and construct a generalized neural network which has some good qualitative behavior, e.g., ang number of isolated prototypes can be set to asymptotically stable fixpoints, and any track converges to one of the equilibriums. The time/space complexity of our model is O(mn), other than 0(nn) of Hopfield-like models. Simulation experiment shows its good recognition ability. © 1992 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic artist recognition of songs using a hierarchic structure

Automatic artist recognition of songs using a hierarchic str...

引用

China-Ireland International Conference on Information and Communications Technologies, CIICT 2007

作者： Zhu, Song-Hao Liu, Yun-Cai Institute of Image Process and Pattern Recognition Shanghai Jiao tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9780863418273

In this paper, we develop a hierarchic structure to complete the reorganization of artist automatically. This proposed system can efficiently identify the artist's voice of a raw song by analyzing substantive features extracted from both pure music and singing song mixed with accompanying music. The silent segments of a raw song are firstly detected and removed. Then, the pure music segments are distinguished from the segments of singing song mixed with accompanying music by support vector machines based on learning from the training data. Furthermore, the singing voice is recognized by the clustering results and the domain knowledge related to properties of the accompanying music and voice. The experiments on different genres of songs illustrate our proposed system is possible.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

image annotation refinement using semantic similarity correlation

Image annotation refinement using semantic similarity correl...

引用

作者： Zhu, Songhao Liu, Yuncai Institute of Image Process and Pattern Recognition Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9781424421756

Automatic image annotation is a promising way to achieve more effective image management and retrieval by using keywords. However, system performances of the existing state-of-the-art keyword annotation schemes are often not so satisfactory. Therefore, image annotation refinement is crucial to improve the imprecise annotation results. In this paper, a novel approach is developed to automatically refine the initial annotation of images. First, for a query image, the candidate annotations are obtained by a step-up model-based algorithm using perceptual visual characteristic. Then, a refine algorithm, fast random walk with restart is used to re-rank the candidate annotations and the top ones are reserved as the final annotations. Experiments conducted on the typical Corel dataset shows that the proposed scheme can effectively improve the automatic annotation performance. © 2008 IEEE.

关键词： image annotation

来源：评论

学校读者我要写书评

暂无评论

Segmenting video shots using 2D entropy model

Segmenting video shots using 2D entropy model

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Songhao Zhu Yuncai Liu Institute of Image Process and Pattern Recognition Shanghai Jiaotong University Shanghai China

A shot presents a contiguous action recorded by an uninterrupted camera operation and frames within a shot keep spatio-temporal coherence. Segmenting a serial video stream file into meaning shots is the first pass for the task of video analysis, content-based video understanding. In this paper, a hierarchical framework based on an improved two-dimensional entropy model is proposed to complete the purpose of the partition of video shots. Our approach first selects the transition boundary candidates in the state of desampling. Then these detected transition candidates are further classified into cut or gradual type, and at the same time the falsely detected shot breaks can be distinguished and merged into the normal shot based on the human perception principle of visual content. Moreover, the boundary of gradual transition can be precisely located using characteristic features of gradual transition. A large number of video sequences are used to test our system performance and promising results have been obtained.

关键词： Entropy Pixel Video sequences Visualization Lighting Cameras Streaming media

来源：评论

学校读者我要写书评

暂无评论

image annotation refinement using semantic similarity correlation

Image annotation refinement using semantic similarity correl...

引用

International Conference on pattern recognition

作者： Songhao Zhu Yuncai Liu Institute of Image Process and Pattern Recognition Shandong Jiaotong University Shanghai China

ISBN: (纸本)9781424421749

关键词： image retrieval Content based retrieval Digital images Testing pattern recognition Linear discriminant analysis Machine learning Support vector machines Support vector machine classification Web search

来源：评论

学校读者我要写书评

暂无评论

A synthesis procedure for a generalized neural network

A synthesis procedure for a generalized neural network

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yan Yan Jie Gu Li Institute of Image Process and Pattern Recognition Shanghai Jiaotong University Shanghai China

ISBN: (纸本)0780305590

An FTTB (from top to bottom) design strategy for a neural network is introduced. From the scheme the authors present a design method and construct a generalized neural network which has some good qualitative behavior, e.g. any number of isolated prototypes can be set to asymptotically stable fixpoints, and any track converges to one of the equilibria. The time/space complexity of the model is O(mn), as opposed to O(nn) of Hopfield-like models. A simulation experiment shows its good recognition ability.< >

关键词： Network synthesis Neural networks Prototypes Brain modeling Nervous system Biological neural networks Neurons Circuits Power system modeling Costs

来源：评论

学校读者我要写书评

暂无评论

A novel scheme for video scenes segmentation and semantic representation

A novel scheme for video scenes segmentation and semantic re...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Songhao Zhu Yuncai Liu Institute of Image Process and Pattern Recognition Shanghai Jiaotong University Shanghai China

Grouping video contents into semantic segments is the crucial pass to content-based video summarization and retrieval. In this paper, we present a novel scene segmentation and semantic representation scheme for various video types. We first detect video shot using a coarse-to-fine algorithm. The key frames without useful information are detected and removed using template matching. Spatio-temporal coherent shots are then grouped into the same scene based on the temporal constraint of video content and visual similarity of shot activity. With general editing technique used in the continuously recorded video, semantic representation of scene content is specified to satisfy human demand on video retrieval. The proposed algorithm has been performed on various types of videos containing movie and TV program. Promising experimental results shows that the proposed method makes sense to efficient retrieval of video contents of interest.

关键词： Correlation Integrated circuits Feature extraction Interviews Visualization Testing Histograms

来源：评论

学校读者我要写书评

暂无评论

Fingerprint preclassification using key-points

Fingerprint preclassification using key-points

引用

International Symposium on Speech, image processing and Neural Networks

作者： Ying Shan Peng Fei Shi Jie Gu Li Inst. of Image Process. & Pattern Recognition Shanghai Jiaotong Univ. China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

ISBN: (纸本)078031865X

A new idea of fingerprint preclassification named the key-point recognition method (KMF) is proposed which only pays attention to whether there is a general feature key-point in a certain area and takes no notice of what the feature is. Using this method, an automatic fingerprint recognition system has been developed, which is characterized by fewer requirements imposed on the preprocessing, lower sensitivity to the noise, higher capacity and parallelism being compared with other traditional ones. The system can list out the most promising fingerprints as a preclassifier.< >

关键词： Fingerprint recognition Equations Lattices Labeling Supervised learning Energy measurement Frequency measurement Brightness Convergence Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Integration of physical and chemical treatment on the extraction of starch from Canna edulis Ker. rhizome

Integration of physical and chemical treatment on the extrac...

引用

2013 World Congress on Engineering and Technology(CET 2013)

作者： Judy R.B.Witono Herry Santoso Y.I.P.Arry Miryanti Daniel Tan Gordon Life Science Institute Institute of Image Process ＆ Pattern Recognition Shanghai Jiao Tong University

The extraction of Canna edulis Ker. starch from its rhizome was performed using 2 different types of press （hydraulic press and screw press） and with the addition of Na-metabisulphite and NaOH （in the range of concentration 100 5000 ppm each）. The optimum condition for this process was determined by Central Composite Design of experiment and the statistical calculation was solved by Design-Expert 7.0.0. The targets of the observed responses were high starch yield, low ash, low fiber, and high carbohydrate content. The results showed that the starch yield and the reduction of fiber were only influenced by the physical treatment whereas ash content in the product was influenced by both the NaOH concentration and physical treatment. The carbohydrate content in the extraction product was affected by NaOH, by the interaction between the concentrations of NaOH and Na 2 S 2 O 5 and also by the physical treatment. The hydraulic press gives much better responses compared to the screw press. But in the selected range of additives concentrations, the screw press gives a higher starch yield （30%-52%）.

关键词： Canna edulis Ker. Central Composite Design of Experiment Hydraulic Press Screw Press Starch Extraction

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：