Automatic image–text alignment for large-scale web image indexing and retrieval

In this paper, an automatic image–text alignment algorithm is developed to achieve more effective indexing and retrieval of large-scale web images by aligning web images with their most relevant auxiliary text terms or phrases. First, a large number of cross-media web pages (which contain web images and their auxiliary texts) are crawled and segmented into a set of image–text pairs (informative web images and their associated text terms or phrases). Second, near-duplicate image clustering is used to group large-scale web images into a set of clusters of near-duplicate images according to their visual similarities. The near-duplicate web images in the same cluster share similar semantics and are simultaneously associated with a same or similar set of auxiliary text terms or phrases which co-occur frequently in the relevant text blocks, thus performing near-duplicate image clustering can significantly reduce the uncertainty on the relatedness between the semantics of web images and their auxiliary text terms or phrases. Finally, random walk is performed over a phrase correlation network to achieve more precise image–text alignment by refining the relevance scores between the web images and their auxiliary text terms or phrases. Our experiments on algorithm evaluation have achieved very positive results on large-scale cross-media web pages.     

A non-parametric visual-sense model of images—extending the cluster hypothesis beyond text

The main challenge of a search engine is to find information that are relevant and appropriate. However, this can become difficult when queries are issued using ambiguous words. Rijsbergen first hypothesized a clustering approach for web pages wherein closely associated pages are treated as a semantic group with the same relevance to the query (Rijsbergen 1979). In this paper, we extend Rijsbergen’s cluster hypothesis to multimedia content such as images. Given a user query, the polysemy in the return image set is related to the many possible meanings of the query. We develop a method to cluster the polysemous images into their semantic categories. The resulting clusters can be seen as the visual senses of the query, which collectively embody the visual interpretations of the query. At the heart of our method is a non-parametric Bayesian approach that exploits the complementary text and visual information of images for semantic clustering. Latent structures of polysemous images are mined using the Hierarchical Dirichlet Process (HDP). HDP is a non-parametric Bayesian model that represents images using a mixture of components. The main advantage of our model is that the number of mixture components is not fixed a priori, but is determined during the posterior inference process. This allows our model to grow with the level of polysemy (and visual diversity) of images. The same set of components is used to model all images, with only the mixture weights varying amongst images. Evaluation results on a large collection of web images show the efficacy of our approach.     

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.     

Multimodal Retrieval using Mutual Information based Textual Query Reformulation

Multimodal Retrieval is a well-established approach for image retrieval. Usually, images are accompanied by text caption along with associated documents describing the image. Textual query expansion as a form of enhancing image retrieval is a relatively less explored area. In this paper, we first study the effect of expanding textual query on both image and its associated text retrieval. Our study reveals that judicious expansion of textual query through keyphrase extraction can lead to better results, either in terms of text-retrieval or both image and text-retrieval. To establish this, we use two well-known keyphrase extraction techniques based on tf-idf and KEA. While query expansion results in increased retrieval efficiency, it is imperative that the expansion be semantically justified. So, we propose a graph-based keyphrase extraction model that captures the relatedness between words in terms of both mutual information and relevance feedback. Most of the existing works have stressed on bridging the semantic gap by using textual and visual features, either in combination or individually. The way these text and image features are combined determines the efficacy of any retrieval. For this purpose, we adopt Fisher-LDA to adjudge the appropriate weights for each modality. This provides us with an intelligent decision-making process favoring the feature set to be infused into the final query. Our proposed algorithm is shown to supersede the previously mentioned keyphrase extraction algorithms for query expansion significantly. A rigorous set of experiments performed on ImageCLEF-2011 Wikipedia Retrieval task dataset validates our claim that capturing the semantic relation between words through Mutual Information followed by expansion of a textual query using relevance feedback can simultaneously enhance both text and image retrieval.     

Improving image tags by exploiting web search results

Automatic image tagging automatically assigns image with semantic keywords called tags, which significantly facilitates image search and organization. Most of present image tagging approaches are constrained by the training model learned from the training dataset, and moreover they have no exploitation on other type of web resource (e.g., web text documents). In this paper, we proposed a search based image tagging algorithm (CTSTag), in which the result tags are derived from web search result. Specifically, it assigns the query image with a more comprehensive tag set derived from both web images and web text documents. First, a content-based image search technology is used to retrieve a set of visually similar images which are ranked by the semantic consistency values. Then, a set of relevant tags are derived from these top ranked images as the initial tag set. Second, a text-based search is used to retrieve other relevant web resources by using the initial tag set as the query. After the denoising process, the initial tag set is expanded with other tags mined from the text-based search result. Then, an probability flow measure method is proposed to estimate the probabilities of the expanded tags. Finally, all the tags are refined using the Random Walk with Restart (RWR) method and the top ones are assigned to the query images. Experiments on NUS-WIDE dataset show not only the performance of the proposed algorithm but also the advantage of image retrieval and organization based on the result tags.     

MQSS: multimodal query suggestion and searching for video search

In this paper, we propose a multimodal query suggestion method for video search which can leverage multimodal processing to improve the quality of search results. When users type general or ambiguous textual queries, our system MQSS provides keyword suggestions and representative image examples in an easy-to-use dropdown manner which can help users specify their search intent more precisely and effortlessly. It is a powerful complement to initial queries. After the queries are formulated as multimodal query (i.e., text, image), the new queries are input to individual search models, such as text-based, concept-based and visual example-based search model. Then we apply multimodal fusion method to aggregate the above-mentioned several search results. The effectiveness of MQSS is demonstrated by evaluations over a web video data set.     

基于文本与语义相关性分析的图像检索

为了更加有效地检索到符合用户复杂语义需求的图像，提出一种基于文本描述与语义相关性分析的图像检索算法。该方法将图像检索分为两步：基于文本语义相关性分析的图像检索和基于SIFT特征的相似图像扩展检索。根据自然语言处理技术分析得到用户文本需求中的关键词及其语义关联，在选定图像库中通过语义相关性分析得到“种子”图像；接下来在图像扩展检索中，采用基于SIFT特征的相似图像检索，利用之前得到的“种子”图像作为查询条件，在网络图像库中进行扩展检索，并在结果集上根据两次检索的图像相似度进行排序输出，最终得到更加丰富有效的图像检索结果。为了证明算法的有效性，在标准数据集Corel5K和网络数据集Deriantart8K上完成了多组实验，实验结果证明该方法能够得到较为精确地符合用户语义要求的图像检索结果，并且通过扩展算法可以得到更加丰富的检索结果。     

融合Copulas理论和关联规则挖掘的查询扩展

将Copulas理论引入文本特征词关联模式挖掘,提出融合Copulas理论和关联规则挖掘的查询扩展算法.从初检文档集中提取前列n篇文档构建伪相关反馈文档集或用户相关反馈文档集,利用基于Copulas理论的支持度和置信度对相关反馈文档集挖掘含有原查询词项的特征词频繁项集和关联规则模式,从这些规则模式中提取扩展词,实现查询扩展.在NTCIR-5 CLIR中英文本语料上的实验表明,文中算法可有效遏制查询主题漂移和词不匹配问题,改善信息检索性能,提升扩展词质量,减少无效扩展词.     

Ensemble of multiple instance classifiers for image re-ranking

Text-based image retrieval may perform poorly due to the irrelevant and/or incomplete text surrounding the images in the web pages. In such situations, visual content of the images can be leveraged to improve the image ranking performance. In this paper, we look into this problem of image re-ranking and propose a system that automatically constructs multiple candidate “multi-instance bags (MI-bags)”, which are likely to contain relevant images. These automatically constructed bags are then utilized by ensembles of Multiple Instance Learning (MIL) classifiers and the images are re-ranked according to the final classification responses. Our method is unsupervised in the sense that, the only input to the system is the text query itself, without any user feedback or annotation. The experimental results demonstrate that constructing multiple instance bags based on the retrieval order and utilizing ensembles of MIL classifiers greatly enhance the retrieval performance, achieving on par or better results compared to the state-of-the-art.     

Automatic image annotation and retrieval using group sparsity

Automatically assigning relevant text keywords to images is an important problem. Many algorithms have been proposed in the past decade and achieved good performance. Efforts have focused upon model representations of keywords, whereas properties of features have not been well investigated. In most cases, a group of features is preselected, yet important feature properties are not well used to select features. In this paper, we introduce a regularization-based feature selection algorithm to leverage both the sparsity and clustering properties of features, and incorporate it into the image annotation task. Using this group-sparsity-based method, the whole group of features [e.g., red green blue (RGB) or hue, saturation, and value (HSV)] is either selected or removed. Thus, we do not need to extract this group of features when new data comes. A novel approach is also proposed to iteratively obtain similar and dissimilar pairs from both the keyword similarity and the relevance feedback. Thus, keyword similarity is modeled in the annotation framework. We also show that our framework can be employed in image retrieval tasks by selecting different image pairs. Extensive experiments are designed to compare the performance between features, feature combinations, and regularization-based feature selection methods applied on the image annotation task, which gives insight into the properties of features in the image annotation task. The experimental results demonstrate that the group-sparsity-based method is more accurate and stable than others.     

The effects of multiple query evidences on social image retrieval

System performance assessment and comparison are fundamental for large-scale image search engine development. This article documents a set of comprehensive empirical studies to explore the effects of multiple query evidences on large-scale social image search. The search performance based on the social tags, different kinds of visual features and their combinations are systematically studied and analyzed. To quantify the visual query complexity, a novel quantitative metric is proposed and applied to assess the influences of different visual queries based on their complexity levels. Besides, we also study the effects of automatic text query expansion with social tags using a pseudo relevance feedback method on the retrieval performance. Our analysis of experimental results shows a few key research findings: (1) social tag-based retrieval methods can achieve much better results than content-based retrieval methods; (2) a combination of textual and visual features can significantly and consistently improve the search performance; (3) the complexity of image queries has a strong correlation with retrieval results’ quality—more complex queries lead to poorer search effectiveness; and (4) query expansion based on social tags frequently causes search topic drift and consequently leads to performance degradation.     

Graph based Ranked Answers for Keyword Graph Structure

Keyword query processing over graph structured data is beneficial across various real world applications. The basic unit, of search and retrieval, in keyword search over graph, is a structure (interconnection of nodes) that connects all the query keywords. This new answering paradigm, in contrast to single web page results given by search engines, brings forth new challenges for ranking. In this paper, we propose a simple but effective Fuzzy set theory based Ranking measure, called FRank. Fuzzy sets acknowledge the contribution of each individual query keyword, discretely, to enumerate node relevance. A novel aggregation operator is defined, to combine the content relevance based fuzzy sets and, compute query dependent edge weights. The final rank, of an answer, is computed by non-monotonic addition of edge weights, as per their relevance to keyword query. FRank evaluates each answer based on the distribution of query keywords and structural connectivity between those keywords. An extensive empirical analysis shows superior performance by our proposed ranking measure as compared to the ranking measures adopted by current approaches in the literature.     

一种基于稀疏典型性相关分析的图像检索方法

图像语义检索的一个关键问题就是要找到图像底层特征与语义之间的关联,由于文本是表达语义的一种有效手段,因此提出通过研究文本与图像两种模态之间关系来构建反映两者间潜在语义关联的有效模型的思路,基于该模型,可使用自然语言形式(文本语句)来表达检索意图,最终检索到相关图像.该模型基于稀疏典型性相关分析(sparse canonical correlation analysis,简称sparse CCA),按照如下步骤训练得到:首先利用隐语义分析方法构造文本语义空间,然后以视觉词袋(bag of visual words)来表达文本所对应的图像,最后通过Sparse CCA算法找到一个语义相关空间,以实现文本语义与图像视觉单词间的映射.使用稀疏的相关性分析方法可以提高模型可解释性和保证检索结果稳定性.实验结果验证了Sparse CCA方法的有效性,同时也证实了所提出的图像语义检索方法的可行性.     

Narrowing the semantic gap - improved text-based web document retrieval using visual features

We present the results of our work that seek to negotiate the gap between low-level features and high-level concepts in the domain of web document retrieval. This work concerns a technique, called the latent semantic indexing (LSI), which has been used for textual information retrieval for many years. In this environment, LSI determines clusters of co-occurring keywords so that a query which uses a particular keyword can then retrieve documents perhaps not containing this keyword, but containing other keywords from the same cluster. In this paper, we examine the use of this technique for content-based web document retrieval, using both keywords and image features to represent the documents. Two different approaches to image feature representation, namely, color histograms and color anglograms, are adopted and evaluated. Experimental results show that LSI, together with both textual and visual features, is able to extract the underlying semantic structure of web documents, thus helping to improve the retrieval performance significantly, even when querying is done using only keywords.     

An adaptive technique for content-based image retrieval

We discuss an adaptive approach towards Content-Based Image Retrieval. It is based on the Ostensive Model of developing information needs—a special kind of relevance feedback model that learns from implicit user feedback and adds a temporal notion to relevance. The ostensive approach supports content-assisted browsing through visualising the interaction by adding user-selected images to a browsing path, which ends with a set of system recommendations. The suggestions are based on an adaptive query learning scheme, in which the query is learnt from previously selected images. Our approach is an adaptation of the original Ostensive Model based on textual features only, to include content-based features to characterise images. In the proposed scheme textual and colour features are combined using the Dempster-Shafer theory of evidence combination. Results from a user-centred, work-task oriented evaluation show that the ostensive interface is preferred over a traditional interface with manual query facilities. This is due to its ability to adapt to the user's need, its intuitiveness and the fluid way in which it operates. Studying and comparing the nature of the underlying information need, it emerges that our approach elicits changes in the user's need based on the interaction, and is successful in adapting the retrieval to match the changes. In addition, a preliminary study of the retrieval performance of the ostensive relevance feedback scheme shows that it can outperform a standard relevance feedback strategy in terms of image recall in category search.     

A survey of content-based image retrieval with high-level semantics

In order to improve the retrieval accuracy of content-based image retrieval systems, research focus has been shifted from designing sophisticated low-level feature extraction algorithms to reducing the ‘semantic gap’ between the visual features and the richness of human semantics. This paper attempts to provide a comprehensive survey of the recent technical achievements in high-level semantic-based image retrieval. Major recent publications are included in this survey covering different aspects of the research in this area, including low-level image feature extraction, similarity measurement, and deriving high-level semantic features. We identify five major categories of the state-of-the-art techniques in narrowing down the ‘semantic gap’: (1) using object ontology to define high-level concepts; (2) using machine learning methods to associate low-level features with query concepts; (3) using relevance feedback to learn users’ intention; (4) generating semantic template to support high-level image retrieval; (5) fusing the evidences from HTML text and the visual content of images for WWW image retrieval. In addition, some other related issues such as image test bed and retrieval performance evaluation are also discussed. Finally, based on existing technology and the demand from real-world applications, a few promising future research directions are suggested.     

A knowledge-based approach for retrieving images by content

A knowledge based approach is introduced for retrieving images by content. It supports the answering of conceptual image queries involving similar-to predicates, spatial semantic operators, and references to conceptual terms. Interested objects in the images are represented by contours segmented from images. Image content such as shapes and spatial relationships are derived from object contours according to domain specific image knowledge. A three layered model is proposed for integrating image representations, extracted image features, and image semantics. With such a model, images can be retrieved based on the features and content specified in the queries. The knowledge based query processing is based on a query relaxation technique. The image features are classified by an automatic clustering algorithm and represented by Type Abstraction Hierarchies (TAHs) for knowledge based query processing. Since the features selected for TAH generation are based on context and user profile, and the TAHs can be generated automatically by a clustering algorithm from the feature database, our proposed image retrieval approach is scalable and context sensitive. The performance of the proposed knowledge based query processing is also discussed     

Content based image retrieval via a transductive model

Content based image retrieval plays an important role in the management of a large image database. However, the results of state-of-the-art image retrieval approaches are not so satisfactory for the well-known gap between visual features and semantic concepts. Therefore, a novel transductive learning scheme named random walk with restart based method (RWRM) is proposed, consisting of three major components: pre-filtering processing, relevance score calculation, and candidate ranking refinement. Firstly, to deal with the problem of large computation cost involved in a large image database, a pre-filtering processing is utilized to filter out the most irrelevant images while keeping the most relevant images according to the results of a manifold ranking algorithm. Secondly, the relevance between a query image and the remaining images are obtained with respect to the probability density estimation. Finally, a transductive learning model, namely a random walk with restart model, is utilized to refine the ranking taking into account both the pairwise information of unlabeled images and the relevance scores between query image and unlabeled images. Experiments conducted on a typical Corel dataset demonstrate the effectiveness of the proposed scheme.     

Density-based spatial keyword querying

With the rocket development of the Internet, WWW(World Wide Web), mobile computing and GPS (Global Positioning System) services, location-based services like Web GIS (Geographical Information System) portals are becoming more and more popular. Spatial keyword queries over GIS spatial data receive much more attention from both academic and industry communities than ever before. In general, a spatial keyword query containing spatial location information and keywords is to locate a set of spatial objects that satisfy the location condition and keyword query semantics. Researchers have proposed many solutions to various spatial keyword queries such as top-K keyword query, reversed kNN keyword query, moving object keyword query, collective keyword query, etc. In this paper, we propose a density-based spatial keyword query which is to locate a set of spatial objects that not only satisfies the query’s textual and distance condition, but also has a high density in their area. We use the collective keyword query semantics to find in a dense area, a group of spatial objects whose keywords collectively match the query keywords. To efficiently process the density based spatial keyword query, we use an IR-tree index as the base data structure to index spatial objects and their text contents and define a cost function over the IR-tree indexing nodes to approximately compute the density information of areas. We design a heuristic algorithm that can efficiently prune the region according to both the distance and region density in processing a query over the IR-tree index. Experimental results on datasets show that our method achieves desired results with high performance.     

Methods for dictionary generation

A classification of lexicographic resources is proposed to support automatic textanalysis systems. Four types of dictionaries are distinguished and described, namely, terminological, terminological-statistical, thesauri, and ontologies. Methods for dictionary generation are divided into static and dynamic, as well as linear and stepwise. Methods for weighting terms are divided into intertextual and intratextual. The features of the TF*IDF algorithm are considered in detail. Two techniques for dictionary generation are described.