相似性检索

基于长期学习的多媒体数据库相似性检索

A Long-Term Learning Based Similarity Retrieval of Multimedia Database

基于小波变换的文档相似性检索方法

Algorithms for theses similarity retrieval based on wavelet transform

P2P网络中高维数据对象相似性检索方法研究

Research on Similarity Search for High-dimensional Data Objects in P2P Networks

因此将CM-tree进行改造，使它适用于多度量空间，进而支持动态相似性检索。

But it does not apply to multi-metric spaces . Therefore , transformation is carried out on the CM-tree to make it suitable for multi-metric spaces and dynamic similarity search .

提出了利用角检测技术进行图像的相似性检索。

Proposed a new image retrieval method using corner detection .

多准则框架下的蛋白质三维结构相似性检索

A Multiple Criteria Framework for 3D Protein Structure Similarity Retrieval

基于关键词聚类的论文相似性检索

Algorithms Based on Keywords clustering for Theses Similarity Search

基于直方图的遥感图像相似性检索方法比较

Comparative Studies on Similarity Measures for Remote Sensing Image Retrieval Based on Histogram

图像数据库中虚图像的相似性检索

Similarity Retrieval of Virtual Images in Image Database

基于多重倒排文件的快速相似性检索

Fast Similarity Retrieval Based on Multiple-Inverted File

相似性检索已经成为信息检索中的一个重要研究领域。

Now , the retrieval of similar objects becomes a very important research issue in information retrieval .

在相似性检索时，根据概念向量计算论文的相似性，把与给定论文最相似的论文返回给用户。用这种算法，能很好的对论文进行基于概念的相似性检索。

With this algorithm , we propose a method for theses retrieval , which based on concept similarity .

然而，在现有的大多数相似性检索中，对信息对象采用的度量方式为单度量。

However , the majority of the existing similarity retrieval of information objects is used for single-metric measurement .

另外，在该索引上进行动态相似性检索测试，以验证改进后的索引对多度量动态相似性检索的适用性和有效性。

In addition , applicability and validity of the index for multi-metric similarity search is validated by the dynamic similarity retrieval testing .

目前，基于内容的图像数据库检索已成为图像数据库研究的主流，其核心是基于内容的图像相似性检索。

CBIR is a core technique of image database system . The main obstacle facing content-based image database is that the retrieval effectiveness is not satisfiable .

相似性检索是个非常关键的问题，即在数据集中找到与某个对象相似性较大的数据。

Similarity retrieval is a very critical issue , which is to find a more similar data with the given object in the large data set .

图像数据库容量的增长，迫切需要研究高效的索引技术来支持快速相似性检索的要求。

As the volume of image database grows , it is urged to work over high effective index technique to support fast similarity search in very large databases .

实验结果显示，关键维能够很好地提高索引的相似性检索性能，对于加速基于内容的多媒体信息检索具有很大的意义。

Experimental results show that key dimension can be used to improve the performance of index , which is of great significance for accelerating the content based similarity search .

该系统提供文献间的相似性检索，实现了数据的关联分析，提高了中医药文献的查全率。

The method includes query expansion , similarity retrieval , association analysis , and so on , enables similarity retrieval of documents and the association analysis of TCM information .

随着信息爆炸式的增长，相似性检索被越来越多地应用于非结构化数据库中，例如图像库、三维对象库、生物序列库等。

With the explosive growth of information , similarity search is used more and more in unstructured database , such as images , 3D objects , sequences and so on .

文中给出了该索引结构并详细介绍了相关索引算法.实验结果表明，该索引结构显著提高了高维数据空间中相似性检索性能。

Described the algorithm for this index structure in detail and provide experimental results , which show it is an effective index structure , which can greatly enhance the similarity search .

基于内容的图像检索，就是根据描述图像内容的特征矢量进行相似性检索，其中图像内容的提取可以是通用的，也可以是基于特定领域的。

Content based image retrieval is to perform the similarity retrieval according to the image features representing the image content , which may be extracted in the generic or specific domain .

为了解决这个问题，现借助于多度量空间搜索来改善相似性检索的效果，并在相似性检索中引入多度量的动态组合来满足用户多变的需求。

To solve this problem , multi-metric space is used to improve the effectiveness of similarity search ; also dynamic combination of multi-metrics is introduced to meet the changing needs of users .

索引机制是数据库和多媒体领域的重要研究课题，很多在大规模数据集里进行相似性检索的应用都需要有效的高维索引结构来加速查询过程。

Indexing schemes are significant research issues in the domain of database and multimedia , efficient indexing schemes for high-dimensional data are required for speeding up the similar searching in the large-scale datasets .

本文针对现有质谱匹配算法在实现物质的相似性检索方面存在的问题，提出了以权重m/z·I为峰的重要性因子的质谱匹配新算法。

Aiming at the problem of existing matching algorithm of mass spectrum in similar substance searching , in this paper , a new matching algorithm was put forward to improve the ability of searching similarity substances using weight factor m / z · I.

第五章介绍了支持产品快速设计的实例检索的具体实现，分析了支持该相似性检索的实例存储结构，同时给出汽配产品相似性检索的策略，最后给出检索模块的关键技术的实现方法。

Chapter ⅴ gives the realization of similarities retrieval of Rapid Product Design , analyses examples storage structure which support the similarities retrieval , gives similarities retrieval strategy of the auto parts , finally present the solution of the key technologies of the retrieval module .

将SS-树索引用于基于内容图像检索的相似性检索，比较了顺序扫描和采用R-树、SS-树进行检索的效率，实验结果表明采用SS-树索引进行基于内容的图像检索是高效可行的。

The efficiency of order scanning is compared with that of retrieving with R-tree and SS-tree . The experiment shows that with the use of index , the efficiency of CBIR is greatly improved . Using SS-tree index to retrieve is efficient and effective for CBIR .

大容量多媒体数据库的基于内容相似性的检索本质上是高维特征空间中一定距离函数的K近邻问题。

Searches based on content similarities in large multimedia libraries are essentially K nearest neighbor searches in high dimensional spaces .

该方法根据零件的宏观特征，利用检索法检索出CASE库中与零件宏观特征相匹配的类型，再根据零件的几何造型、属性和材料相似性迅速检索出与设计零件最相似的零件。

On the basis of macroscopic characteristics of components , the algorithm found out the types of components in CASE library which matches to the macroscopic characteristics of components , and searched the most similar components according to their geometry constructions , attribute and material similarity .

传统CBIR技术试图通过分析图像视觉特征的相似性来检索图像，这不能满足普通人按语义检索图像的需求。

Traditional techniques of CBIR try to retrieve images through analyzing the similarity of image visual features , but CBIR cannot meet the requirements of semantic image retrieval .