一种新的基于本体论描述的内容图像检索模型

分析了基于内容的图像检索中存在的问题,利用本体论方法建立图像底层特征本体及特定类图像本体.同时,定义了图像描述因子并建立相应的图像组合规则.最后,利用图像的底层特征进行图像检索,结合多分类支持向量机,实现图像底层特征与高层描述信息的关联,进而实现了图像语义检索,缩小了"语义鸿沟"对基于内容的图像检索的影响.实验结果表明本模型能够提高基于内容的图像检索的准确率,同时,经过3～5次反馈,可以实现语义检索功能.     

多模型融合的多标签图像自动标注

为了实现更为准确的复杂语义内容图像理解,提出一种融合多模型的多标签图像自动标注方法.该方法采用3个不同的模型分别对图像语义内容进行分析:在前景语义概念检测中,提出一种基于多特征的视觉显著性分析方法,并利用多Nystrm近似核对前景对象的语义进行判别分析;对于背景概念检测,提出一种区域语义分析的方法;通过构造基于潜语义分析的语义相关矩阵来消除标注错误的标签.根据前景和背景的语义和视觉特征,分别采用不同的模型提取前景和背景标注词,而语义相关分析能够有效地提高标注的准确性.实验结果表明,该多模型融合标注方法在图像的深层语义分析以及多标签标注方面具有较好的效果;与同类算法相比,能够有效地减少错误标注的标签数目,得到更加准确的标注结果.     

基于概念索引的图像自动标注

在基于内容的图像检索中,建立图像底层视觉特征与高层语义的联系是个难题.一个新的解决方法是按照图像的语义内容进行自动标注.为了缩小语义差距,采用基于支持向量机(SVM)的多类分类器为空间映射方法,将图像的底层特征映射为具有一定高层语义的模型特征以实现概念索引,使用的模型特征为多类分类的结果以概率形式组合而成.在模型特征组成的空间中,再使用核函数方法对关键词进行了概率估计,从而提供概念化的图像标注以用于检索.实验表明,与底层特征相比,使用模型特征进行自动标注的结果F度量相对提高14%.     

基于随机点积图的图像标注改善算法

针对自动图像标注中底层特征和高层语义之间的鸿沟问题,提出一种基于随机点积图的图像标注改善算法。该算法首先采用图像底层特征对图像候选标注词建立语义关系图,然后利用随机点积图对其进行随机重构,从而挖掘出训练图像集中丢失的语义关系,最后采用重启式随机游走算法,实现图像标注改善。该算法结合了图像的底层特征与高层语义,有效降低了图像集规模变小对标注的影响。在3种通用图像库上的实验证明了该算法能够有效改善图像标注,宏F值与微平均F值最高分别达到0.784与0.743。     

使用基于SVM的否定概率和法的图像标注

在基于内容的图像检索中,建立图像底层视觉特征与高层语义的联系是个难题.对此提出了一种为图像提供语义标签的标注方法.先建立小规模图像库为训练集,库中每个图像标有单一的语义标签,再利用其底层特征,以SVM为子分类器,“否定概率和”法为合成方法构建基于成对耦合方式（PWC）的多类分类器,并对未标注的图像进行分类,结果以N维标注向量表示,实验表明,与一对多方式（OPC）的多类分类器及使用概率和法的PWC相比,“否定概率和”法性能更好.     

基于多特征融合与PLSA-GMM的图像自动标注

为减少图像检索中图像信息的缺失与语义鸿沟的影响,提出了一种基于多特征融合与PLSA-GMM的图像自动标注方法.首先,提取图像的颜色特征、形状特征和纹理特征,三者融合作为图像的底层特征;然后,基于概率潜在语义分析(PLSA)与高斯混合模型(GMM)建立图像底层特征、视觉语义主题与标注关键词间的联系,并基于该模型实现对图像的自动标注.采用Corel 5k数据库进行验证,实验结果证明了本文方法的有效性.     

FAC算法在图像检索中的应用

在自动标注系统中,底层特征转换成高层标注的准确度较低。为此,将自动标注系统中的底层视觉特征和社会标注系统中的高级语义相结合,提出一种新的图像语义标注算法——FAC算法。从自动标注系统和flickr网站用户中得到候选标注,利用图像标注推荐策略获取推荐标注,根据WordNet语义词典中的语义关系,精简出最终的标注集合。实验结果表明,与传统的自动标注算法相比,FAC算法的准确度较高。     

基于SVM算法的图像自动标注

伴随着存储技术以及网络技术的飞速发展,以图像形式来表现大量有效信息成为有效手段。这样一来,怎样实现对海量图像库的有效检索和管理已经非常重要,而其中语义清晰又是重中之重。在图像自动标注技术中,基于图像底层视觉特征的标注技术能够完成,利用图像的底层特征中提取出高级语义信息来标注待标注图像。通过SVM(Support Vector Machine)支持向量机学习方法来自动获取图像高级语义信息关键字,来完成图像的自动标注具有深远的研究意义。     

图像语义自动标注及其粒度分析方法

缩小图像低层视觉特征与高层语义之间的鸿沟, 以提高图像语义自动标注的精度, 进而快速满足用户检索图像的需求,一直是图像语义自动标注研究的关键. 粒度分析方法是一种层次的、重要的数据分析方法, 为复杂问题的求解提供了新的思路. 图像理解与分析的粒度不同, 图像语义标注的精度则不同, 检索的效率及准确度也就不同. 本文对目前图像语义自动标注模型的方法进行综述和分析, 阐述了粒度分析方法的思想、模型及其在图像语义标注过程中的应用, 探索了以粒度分析为基础的图像语义自动标注方法并给出进一步的研究方向.     

基于视觉语义主题的图像自动标注

为减小图像检索中语义鸿沟的影响,提出了一种基于视觉语义主题的图像自动标注方法.首先,提取图像前景与背景区域,并分别进行预处理;然后,基于概率潜在语义分析与高斯混合模型建立图像底层特征、视觉语义主题与标注关键词间的联系,并基于该模型实现对图像的自动标注.采用corel 5数据库进行验证,实验结果证明了本文方法的有效性.     

Learning Pseudo Metric for Intelligent Multimedia Data Classification and Retrieval

While people compare images using semantic concepts, computers compare images using low-level visual features that sometimes have little to do with these semantics. To reduce the gap between the high-level semantics of visual objects and the low-level features extracted from them, in this paper we develop a framework of learning pseudo metrics (LPM) using neural networks for semantic image classification and retrieval. Performance analysis and comparative studies, by experimenting on an image database, show that the LPM has potential application to multimedia information processing.     

一种新的图像语义自动标注模型

根据图像低层特征和高级语义间的对应关系,自动进行图像语义标注是目前图像检索系统研究的热点。简要介绍了基于图像语义连接网络的图像检索框架,提出了一种基于该框架的图像自动标注模型。该模型通过积累用户反馈信息,学习并获得图像语义,从而进行自动的图像标注。图像语义及标注可以在与用户交互过程中得到实时更新。还提出了一种词义相关度分析的方法剔除冗余标注词,解决标注误传播的问题。通过在Corel图像集上的对比实验,验证了该方法的有效性。     

Exploring statistical correlations for image retrieval

Bridging the cognitive gap in image retrieval has been an active research direction in recent years, of which a key challenge is to get enough training data to learn the mapping functions from low-level feature spaces to high-level semantics. In this paper, image regions are classified into two types: key regions representing the main semantic contents and environmental regions representing the contexts. We attempt to leverage the correlations between types of regions to improve the performance of image retrieval. A Context Expansion approach is explored to take advantages of such correlations by expanding the key regions of the queries using highly correlated environmental regions according to an image thesaurus. The thesaurus serves as both a mapping function between image low-level features and concepts and a store of the statistical correlations between different concepts. It is constructed through a data-driven approach which uses Web data (images, their surrounding textual annotations) as training data source to learn the region concepts and to explore the statistical correlations. Experimental results on a database of 10,000 general-purpose images show the effectiveness of our proposed approach in both improving search precision (i.e. filter irrelevant images) and recall (i.e. retrieval relevant images whose context may be varied). Several major factors which have impact on the performance of our approach are also studied.     

A formal framework for image indexing with triples: Toward a concept-based image retrieval

This paper provides a formal specification for concept-based image retrieval using triples. To effectively manage a vast amount of images, we may need an image retrieval system capable of indexing and searching images based on the characteristics of their content. However, such a content-based image retrieval technique alone may not satisfy user queries if retrieved images turn out to be relevant only when they are conceptually related with the queries. In this paper, we develop an image retrieval mechanism to extract semantics of images based on triples. The semantics can be captured by deriving concepts from its constituent objects and spatial relationships between them. The concepts are basically composite objects formed from the aggregation of the constituents. In our mechanism, all the spatial relationships between objects including the concepts are uniformly represented by triples, which are used for indexing images as well as capturing their semantics. We also develop a query evaluation for supporting the concept-based image retrieval. ©1999 John Wiley & Sons, Inc.     

Visual Ontology Construction for Digitized Art Image Retrieval

Current investigations on visual information retrieval are generally content-based methods. The significant difference between similarity in low-level features and similarity in high-level semantic meanings is still a major challenge in the area of image retrieval. In this work, a scheme for constructing visual ontology to retrieve art images is proposed. The proposed ontology describes images in various aspects, including type ＆ style, objects and global perceptual effects. Concepts in the ontology could be automatically derived. Various art image classification methods are employed based on low-level image features. Non-objective semantics are introduced, and how to express these semantics is given. The proposed ontology scheme could make users more naturally find visual information and thus narrows the “semantic gap”. Experimental implementation demonstrates its good potential for retrieving art images in a human-centered manner.     

Relevance Feedback and Learning in Content-Based Image Search

A major bottleneck in content-based image retrieval (CBIR) systems or search engines is the large gap between low-level image features used to index images and high-level semantic contents of images. One solution to this bottleneck is to apply relevance feedback to refine the query or similarity measures in image search process. In this paper, we first address the key issues involved in relevance feedback of CBIR systems and present a brief overview of a set of commonly used relevance feedback algorithms. Almost all of the previously proposed methods fall well into such framework. We present a framework of relevance feedback and semantic learning in CBIR. In this framework, low-level features and keyword annotations are integrated in image retrieval and in feedback processes to improve the retrieval performance. We have also extended framework to a content-based web image search engine in which hosting web pages are used to collect relevant annotations for images and users' feedback logs are used to refine annotations. A prototype system has developed to evaluate our proposed schemes, and our experimental results indicated that our approach outperforms traditional CBIR system and relevance feedback approaches.     

Automatic image semantic interpretation using social action and tagging data

The plethora of social actions and annotations (tags, comments, ratings) from online media sharing Websites and collaborative games have induced a paradigm shift in the research on image semantic interpretation. Social inputs with their added context represent a strong substitute for expert annotations. Novel algorithms have been designed to fuse visual features with noisy social labels and behavioral signals. In this survey, we review nearly 200 representative papers to identify the current trends, challenges as well as opportunities presented by social inputs for research on image semantics. Our study builds on an interdisciplinary confluence of insights from image processing, data mining, human computer interaction, and sociology to describe the folksonomic features of users, annotations and images. Applications are categorized into four types: concept semantics, person identification, location semantics and event semantics. The survey concludes with a summary of principle research directions for the present and the future.     

一种图像底层视觉特征到高层语义的映射方法

基于语义内容的图像检索已经成为解决图像底层特征与人类高层语义之间“语义鸿沟”的关键。根据图像语义检索的思想,提出了一种采用支持向量机(Support Machine Vector)实现图像底层视觉特征到高层语义的映射方法,并在此基础上针对特例库实现了图像的语义标注和检索。实验结果表明,该映射方法能较好地表达人的语义,以提高图像的检索效率。