Learning similarity matching in multimedia content-based retrieval

Many multimedia content-based retrieval systems allow query formulation with the user setting the relative importance of features (e.g., color, texture, shape, etc.) to mimic the user's perception of similarity. However, the systems do not modify their similarity matching functions, which are defined during the system development. We present a neural network-based learning algorithm for adapting the similarity matching function toward the user's query preference based on his/her relevance feedback. The relevance feedback is given as ranking errors (misranks) between the retrieved and desired lists of multimedia objects. The algorithm is demonstrated for facial image retrieval using the NIST Mugshot Identification Database with encouraging results     

一种图像检索中的灰色相关反馈算法

在交互式CBIR系统中，由于用户的查询需求常常是模糊的，因此检索结果从某种意义上说是不确定的。于是，可以将图像检索过程视为一个“灰色系统”，其中的查询向量以及图像特征的权重可视为“灰数”。基于此，该文提出了一种新的相关反馈技术，它采用“灰关联分析”理论来分析和描述“例子图像”与“相关图像”之间的关系，据此自动更新查询向量与图像特征的权重，从而更准确地描述用户的查询需求。实验结果表明，这种相关反馈算法能较好地描述用户的查询需求，显著地改善了图像检索的性能。     

Bayesian relevance feedback for content-based image retrieval

Despite the efforts to reduce the so-called semantic gap between the user's perception of image similarity and the feature-based representation of images, the interaction with the user remains fundamental to improve performances of content-based image retrieval systems. To this end, relevance feedback mechanisms are adopted to refine image-based queries by asking users to mark the set of images retrieved in a neighbourhood of the query as being relevant or not. In this paper, the Bayesian decision theory is used to estimate the boundary between relevant and non-relevant images. Then, a new query is computed whose neighbourhood is likely to fall in a region of the feature space containing relevant images. The performances of the proposed query shifting method have been compared with those of other relevance feedback mechanisms described in the literature. Reported results show the superiority of the proposed method.     

Filter Image Browsing: Interactive Image Retrieval by Using Database Overviews

Human-computer interaction is a decisive factor in effective content-based access to large image repositories. In current image retrieval systems the user refines his query by selecting example images from a relevance ranking. Since the top ranked images are all similar, user feedback often results in rearrangement of the presented images only.For better incorporation of user interaction in the retrieval process, we have developed the Filter Image Browsing method. It also uses feedback through image selection. However, it is based on differences between images rather than similarities. Filter Image Browsing presents overviews of relevant parts of the database to users. Through interaction users then zoom in on parts of the image collection. By repeatedly limiting the information space, the user quickly ends up with a small amount of relevant images. The method can easily be extended for the retrieval of multimedia objects.For evaluation of the Filter Image Browsing retrieval concept, a user simulation is applied to a pictorial database containing 10,000 images acquired from the World Wide Web by a search robot. The simulation incorporates uncertainty in the definition of the information need by users. Results show Filter Image Browsing outperforms plain interactive similarity ranking in required effort from the user. Also, the method produces predictable results for retrieval sessions, so that the user quickly knows if a successful session is possible at all. Furthermore, the simulations show the overview techniques are suited for applications such as hand-held devices where screen space is limited.     

A new evolutionary algorithm combining simulated annealing and genetic programming for relevance feedback in fuzzy information retrieval systems

 Relevance feedback techniques have demonstrated to be a powerful means to improve the results obtained when a user submits a query to an information retrieval system as the world wide web search engines. These kinds of techniques modify the user original query taking into account the relevance judgements provided by him on the retrieved documents, making it more similar to those he judged as relevant. This way, the new generated query permits to get new relevant documents thus improving the retrieval process by increasing recall. However, although powerful relevance feedback techniques have been developed for the vector space information retrieval model and some of them have been translated to the classical Boolean model, there is a lack of these tools in more advanced and powerful information retrieval models such as the fuzzy one. In this contribution we introduce a relevance feedback process for extended Boolean (fuzzy) information retrieval systems based on a hybrid evolutionary algorithm combining simulated annealing and genetic programming components. The performance of the proposed technique will be compared with the only previous existing approach to perform this task, Kraft et al.'s method, showing how our proposal outperforms the latter in terms of accuracy and sometimes also in time consumption. Moreover, it will be showed how the adaptation of the retrieval threshold by the relevance feedback mechanism allows the system effectiveness to be increased.     

基于索引和相关反馈的图像检索研究

在基于图像内容的图像检索(CBIR)系统中,搜索引擎检索图像类似于按照相似标准来查询图像,它应该有足够快的速度并且有较高的检索准确率.索引用来提高系统响应,而相关反馈用于帮助提高检索准确率.在本文中,主要说明基于人感知的相似性度量,以及讨论综合相关反馈的索引方案.该索引方案通过分析特征熵而得出的主从键,而相关反馈是根据Mann-Whitnev检验而提出的,该检验通常用来识别来自同一搜索集中相关图像和不相关图像之间不同特征,并利用不同特征的特点提高检索性能.相关反馈方案针对两不同相似标准来执行,检验判定了这个方法的有效性.最后,把索引机制和相关反馈机制结合起来建立搜索引擎.     

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.     

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.     

Query quality refinement in singular value decomposition to improve genetic algorithms for multimedia data retrieval

With the development of internet and availability of multimedia data capturing devices, the size of Multimedia Digital Database (MDD) collection is increasing rapidly. The complex data presented by such systems do not have the total ordering property presented by the traditional data handled by Database Management Systems (DBMSs). The quality of the search experience in such systems is also normally a big challenge since users from various domains require efficient data searching, browsing and retrieval tools. This has triggered an important research topic in Multimedia information retrieval concerning efficient and effective image similarity search. Modern search algorithms are fast and effective on a wide range of problems, but on MDD with a large number of parameters and observations, manipulations of large matrices, storage and retrieval of large amounts of information may render an otherwise useful method slow or inoperable. The focus of this work is the application of image enhancement technique, using histogram equalization, to the images retrieved using singular value decomposition (SVD). SVD is a linear algebra technique used for discovering correlations within data. The approach, herein referred to as query quality refinement (QQR) technique, improves the image similarity search result, and when incorporated with genetic algorithms further optimizes the search. These beneficial applications can be extended to other different types of multimedia data in various areas such as the P2P and WiMAX networks.     

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.     

Ego-similarity measurement for relevance feedback

Relevance Feedback in Content-Based Image Retrieval is an active field of research. Many mechanisms of Relevance Feedback exist with many interactive techniques and implement criteria. In this paper, we proposed a novel approach of RF which can set adaptive weights of similarity measurement for each database image from the user feedback, i.e. ego-similarity measurement. We would explore the feedback records were archived in the two different ways that stored along with query images (QRF-based) or along with each retrieved relevant image from the image database (DBRF-based). In the experiment, DBRF-based relevant feedback improved greatly in the retrieval effectiveness.     

基于语义的信息检索模型

由于查询与文档中词语的不匹配现象导致一些相关的文档不能被成功地检索出来,在信息检索的研究与实现中,这是影响检索效果的一个很关键的问题。把概念图和知网结合起来,提出对应的相关反馈算法,重新计算词项权重,利用向量空间模型和语义相似度进行语义检索,并给出了语义检索模型。实验结果显示该方法取得了良好的效果。     

An image retrieval system with automatic query modification

Most interactive "query-by-example" based image retrieval systems utilize relevance feedback from the user for bridging the gap between the user's implied concept and the low-level image representation in the database. However, traditional relevance feedback usage in the context of content-based image retrieval (CBIR) may not be very efficient due to a significant overhead in database search and image download time in client-server environments. In this paper, we propose a CBIR system that efficiently addresses the inherent subjectivity in user perception during a retrieval session by employing a novel idea of intra-query modification and learning. The proposed system generates an object-level view of the query image using a new color segmentation technique. Color, shape and spatial features of individual segments are used for image representation and retrieval. The proposed system automatically generates a set of modifications by manipulating the features of the query segment(s). An initial estimate of user perception is learned from the user feedback provided on the set of modified images. This largely improves the precision in the first database search itself and alleviates the overheads of database search and image download. Precision-to-recall ratio is improved in further iterations through a new relevance feedback technique that utilizes both positive as well as negative examples. Extensive experiments have been conducted to demonstrate the feasibility and advantages of the proposed system.     

Automatic content based image retrieval using semantic analysis

We present a new text-to-image re-ranking approach for improving the relevancy rate in searches. In particular, we focus on the fundamental semantic gap that exists between the low-level visual features of the image and high-level textual queries by dynamically maintaining a connected hierarchy in the form of a concept database. For each textual query, we take the results from popular search engines as an initial retrieval, followed by a semantic analysis to map the textual query to higher level concepts. In order to do this, we design a two-layer scoring system which can identify the relationship between the query and the concepts automatically. We then calculate the image feature vectors and compare them with the classifier for each related concept. An image is relevant only when it is related to the query both semantically and content-wise. The second feature of this work is that we loosen the requirement for query accuracy from the user, which makes it possible to perform well on users’ queries containing less relevant information. Thirdly, the concept database can be dynamically maintained to satisfy the variations in user queries, which eliminates the need for human labor in building a sophisticated initial concept database. We designed our experiment using complex queries (based on five scenarios) to demonstrate how our retrieval results are a significant improvement over those obtained from current state-of-the-art image search engines.     

Multimodal retrieval with relevance feedback based on genetic programming

This paper presents a framework for multimodal retrieval with relevance feedback based on genetic programming. In this supervised learning-to-rank framework, genetic programming is used for the discovery of effective combination functions of (multimodal) similarity measures using the information obtained throughout the user relevance feedback iterations. With these new functions, several similarity measures, including those extracted from different modalities (e.g., text, and content), are combined into one single measure that properly encodes the user preferences. This framework was instantiated for multimodal image retrieval using visual and textual features and was validated using two image collections, one from the Washington University and another from the ImageCLEF Photographic Retrieval Task. For this image retrieval instance several multimodal relevance feedback techniques were implemented and evaluated. The proposed approach has produced statistically significant better results for multimodal retrieval over single modality approaches and superior effectiveness when compared to the best submissions of the ImageCLEF Photographic Retrieval Task 2008.     

A Statistical Framework for Image Category Search from a Mental Picture

Starting from a member of an image database designated the "query image," traditional image retrieval techniques, for example, search by visual similarity, allow one to locate additional instances of a target category residing in the database. However, in many cases, the query image or, more generally, the target category, resides only in the mind of the user as a set of subjective visual patterns, psychological impressions, or "mental pictures." Consequently, since image databases available today are often unstructured and lack reliable semantic annotations, it is often not obvious how to initiate a search session; this is the "page zero problem." We propose a new statistical framework based on relevance feedback to locate an instance of a semantic category in an unstructured image database with no semantic annotation. A search session is initiated from a random sample of images. At each retrieval round, the user is asked to select one image from among a set of displayed images-the one that is closest in his opinion to the target class. The matching is then "mental." Performance is measured by the number of iterations necessary to display an image which satisfies the user, at which point standard techniques can be employed to display other instances. Our core contribution is a Bayesian formulation which scales to large databases. The two key components are a response model which accounts for the user's subjective perception of similarity and a display algorithm which seeks to maximize the flow of information. Experiments with real users and two databases of 20,000 and 60,000 images demonstrate the efficiency of the search process.     

Adaptive similarity search for the retrieval of rare events from large time series databases

Improving the recall of information retrieval systems for similarity search in time series databases is of great practical importance. In the manufacturing domain, these systems are used to query large databases of manufacturing process data that contain terabytes of time series data from millions of parts. This allows domain experts to identify parts that exhibit specific process faults. In practice, the search often amounts to an iterative query–response cycle in which users define new queries (time series patterns) based on results of previous queries. This is a well-documented phenomenon in information retrieval and not unique to the manufacturing domain. Indexing manufacturing databases to speed up the exploratory search is often not feasible as it may result in an unacceptable reduction in recall. In this paper, we present a novel adaptive search algorithm that refines the query based on relevance feedback provided by the user. Additionally, we propose a mechanism that allows the algorithm to self-adapt to new patterns without requiring any user input. As the search progresses, the algorithm constructs a library of time series patterns that are used to accurately find objects of the target class. Experimental validation of the algorithm on real-world manufacturing data shows, that the recall for the retrieval of fault patterns is considerably higher than that of other state-of-the-art adaptive search algorithms. Additionally, its application to publicly available benchmark data sets shows, that these results are transferable to other domains.     

An implicit relevance feedback method for CBIR with real-time eye tracking

Relevance feedback is an efficient approach to improve the performance of content-based image retrieval systems, and implicit relevance feedback approaches, which gather users’ feedback by biometric devices (e.g. eye tracker), have extensively investigated in recent years. This paper proposes a novel image retrieval system with implicit relevance feedback, named eye tracking based relevance feedback system (ETRFs). ETRFs is composed of three main modules: image retrieval subsystem based on bag-of-word architecture; user relevance assessment that implicitly acquires relevant images with the help of a modern eye tracker; and relevance feedback module that applies a weighted query expansion method to fuse users’ relevance feedback. ETRFs is implemented online and real-time, which makes it remarkably distinguish from other offline systems. Ten subjects participate our experiments on the dataset of Oxford buildings and UKBench. The experimental results demonstrate that ETRFs achieves notable improvement for image retrieval performance.