CBIR的例句大全

Content-based image retrieval ( CBIR) system is different from traditional retrieval system based on text mode.

所谓基于内容的图像检索系统，具有与传统基于文本的检索系统完全不同的框架。

Content-based image retrieval ( CBIR) is a hotspot of image retrieval at computer filed. It is different from traditional textual retrieval.

基于内容的图像检索是目前计算机图像检索研究的热点，它不同于传统的文本检索，因此将其应用于医学图像领域具有重要意义。

In this paper, we review the development of CBIR and discuss some main techniques of CBIR, including color index, shape index and texture index which are used in image retrieval. Typical commercial and experimental systems of content-based image retrieval are introduced.

综述了基于内容检索技术的进展，并对其主要方法如基于颜色、形状、纹理等图像检索技术进行了论述，介绍了几个典型的基于内容的图像检索系统。

Research and Realization of CBIR System Basted on Domain Color and Its Distribution

基于主色及其分布的CBIR研究和系统实现

Classifying images into reasonable categories using low-level features or annotating images will greatly improve the performance of CBIR systems.

如果事先对图像集合按语义进行合理地分类或者标注，会极大提高CBIR系统的性能。

And the relationship between image metadata and CBIR is also unsubstantial.

基于内容图像检索和图像元数据联系相对薄弱。

Based on the analysis of the information characteristic of image database ( IDB) the general relation schema of IDB and the conception of Content_based Image Retrieval ( CBIR) were investigated, and then a set model of CBIR was introduced.

在分析图像数据库信息特征的基础上，讨论了图像数据库的一般关系模型和图像数据库基于内容查询的定义，提出了相应的集合代数模型，指出遥感图像基于内容查询实现的两种方案。

But the "Semantic Gap" Between the Low-level Features of An Image and High-level Semantic Feature Has Became the Major Obstacle to Cbir Technology.

基于内容的图像检索虽然克服了基于文本检索方法的主观片面和工作量大的缺陷，但是低层视觉特征和高层语义之间的语义鸿沟却成为了基于内容图像检索技术前进的一大障碍。

This paper considers the characteristic of content-based image retrieval ( CBIR) and SAR image together, proposing a method of SAR image retrieval.

本文综合考虑了基于内容的图像检索及SAR图像的特点提出了基于高斯混合模型分类的SAR图像检索方法。

The experimental evaluations show that the proposed asymmetric semi-supervised learning methodology in conjunction with random subspace theory is effective to improve CBIR performance and achieves better performance than some existing approaches.

实验结果表明，不对称的半监督学习策略及随机子空间理论可有效地改进SVM反馈性能，且所提出算法明显优于同类SVM反馈方法。

The SS-tree index is the popular spatial index, and has the characteristics of balance and dynamic, and it's easy to construct and maintain. A web-based CBIR system named IRS is realized by using Java, for which the SS-tree indexes are realized.

SS-树索引是常用的空间数据索引，具有平衡性、动态性、构造和维护的简单性，用Java实现了SS-树索引，并在自行开发的基于内容图像检索实验原型系统IRS中使用。

Content based image retrieval ( CBIR ) is just one of key technologies for such a problem.

基于内容的图象检索 ContentBasedRetrieval,CBIR ) 技术就是解决这一问题的关键技术之一.

The thesis is focused on content-based image retrieval ( CBIR ).

本论文的主要研究内容是基于内容的图像检索.

CBIR with Shape method, very good complete code can be directly used by the test.

基于内容图像检索方法与形状, 非常好完整源代码,可以直接使用.

Content-based image retrieval ( CBIR ) is an advanced project in the recent research area of multimedia retrieval.

基于内容的图像检索 ( CBIR ) 是多媒体检索研究的前沿课题.

This paper discusses the conception and methods of CBIR. Some future research trends are proposed also.

本文较全面地讨论了该技术的基本概念、方法、已取得的成果及今后的一些主要研究方向.

CBIR is a gradually precision process. There is a feature adjustment and rematch process in it.

基于内容的查询和检索是一个逐步求精的过程, 存在一个特征调整、重新匹配的循环过程.

Content Based Image Retrieval CBIR has been a very active research area since 1990's.

基于内容的图像检索是90年代以来逐渐兴起的一个新的研究方向.

CBIR ( Content-Based Image Retrieval) is a very important area of graph analyze and also the difficult of the search engine technology.

基于内容的图像检索（CBIR）是图像分析的一个的重要研究领域，也是目前搜索引擎技术的难点。

Finally, in order to improve the efficiency and accelerate the retrieval process, we give some insight into relevant image database index mechanism. Especially, we discuss thoroughly about M-Tree index mechanism, which we applied in our CBIR system.

最后，为了提高医学图像检索时的速度与效率，我们研究了相关的图像数据库索引机制，并着重讨论了本课题所采用的M-Tree索引机制。