High-Dimensional Image Data Sets Retrieval: Improving Accuracy Using a Weighted Relevance Feedback

Gallas, Abir; Barhoumi, Walid; Zagrouba, Ezzeddine
June 2015
International Journal of Semantic Computing;Jun2015, Vol. 9 Issue 2, p239
Academic Journal
The user's interaction with the retrieval engines, while seeking a particular image (or set of images) in large-scale databases, defines better his request. This interaction is essentially provided by a relevance feedback step. In fact, the semantic gap is increasing in a remarkable way due to the application of approximate nearest neighbor (ANN) algorithms aiming at resolving the curse of dimensionality. Therefore, an additional step of relevance feedback is necessary in order to get closer to the user's expectations in the next few retrieval iterations. In this context, this paper details a classification of the different relevance feedback techniques related to region-based image retrieval applications. Moreover, a technique of relevance feedback based on re-weighting regions of the query-image by selecting a set of negative examples is elaborated. Furthermore, the general context to carry out this technique which is the large-scale heterogeneous image collections indexing and retrieval is presented. In fact, the main contribution of the proposed work is affording efficient results with the minimum number of relevance feedback iterations for high dimensional image databases. Experiments and assessments are carried out within an RBIR system for "Wang" data set in order to prove the effectiveness of the proposed approaches.


Related Articles

  • Image Filtering and Re-ranking Using Data mining Techniques. Prasanna, N. Lakshmi; hirumala Sree G // International Journal of Computer Science & Information Technolo;2014, Vol. 5 Issue 5, p6367 

    Search re-ranking is considered a typical thanks to boost retrieval exactitude. The matter yet isn't trivial particularly once there square measure multiple options or modalities to be thought-about for search, which frequently happens in image and video retrieval. This paper proposes a...

  • Relevance Feedback Based on Particle Swarm Optimize Weight-Vector for Image Retrieval. Feiya LV; Xiaohui YANG; Dengfeng LI // Advanced Materials Research;7/24/2014, Vol. 989-994, p3579 

    As the physical meaning of components are different in feature vector, this paper presents a weight query vector based on QPM to represent the user's true intention more properly, and then proposes two RF frameworks to learn the weights for positives and negatives in the feedback process of CBIR...

  • Personalized document ranking: Exploiting evidence from multiple user interests for profiling and retrieval. Tamine-Lechani, Lynda; Boughanem, Mohand; Zemirli, Nesrine // Journal of Digital Information Management;Oct2008, Vol. 6 Issue 5, p354 

    The goal of personalization in in formation retrieval is to tailor the search engine results to the specific goals, preferences and general interests of the users. We propose a novel model for both user profiling and document ranking that consider the user interests as sources of evidence in...

  • How to be Real and Conventional: A Discussion of the Quality Criteria of Official Statistics. Desrosières, Alain // Minerva: A Review of Science, Learning & Policy;Jul2009, Vol. 47 Issue 3, p307 

    Are the categories used to study the social world and acting on it “real” or “conventional”? An empirical answer to that question is given by an analysis of the debates about the “quality” of statistics produced by the European National Institues of statistics...

  • A course ranking we can all call our own. Russell, Geoff // Golf World;4/25/2008, Vol. 61 Issue 35, p12 

    The author announces the plan to conduct a golf course ranking entitled "Readers' Choice Awards" to be published on the publication "Golf World." The author explained that the aim of the survey is to come up with a list of the best golf course facilities in America both in public and private. He...

  • Passage relevance models for genomics search. Urbain, Jay; Frieder, Ophir; Goharian, Nazli // BMC Bioinformatics;2009 Supplement 3, Vol. 10, Special section p1 

    We present a passage relevance model for integrating syntactic and semantic evidence of biomedical concepts and topics using a probabilistic graphical model. Component models of topics, concepts, terms, and document are represented as potential functions within a Markov Random Field. The...

  • Latent grouping models for user preference prediction. Savia, Eerika; Puolamäki, Kai; Kaski, Samuel // Machine Learning;Jan2009, Vol. 74 Issue 1, p75 

    We tackle the problem of new users or documents in collaborative filtering. Generalization over users by grouping them into user groups is beneficial when a rating is to be predicted for a relatively new document having only few observed ratings. Analogously, generalization over documents...

  • Chapter 7: Statistical Ranking Theory. Tie-Yan Liu // Foundations & Trends in Information Retrieval;2009, Vol. 3 Issue 3, p299 

    Chapter 7 of the book "Foundations and Trends in Information Retrieval," by Tie-Yan Liu is presented. It explores the theoretical framework for pairwise ranking, focusing on the generalization analysis of learning-to-rank methods. It highlights the conventional generalization analysis on ranking...

  • Relevant Points of Interest: a Visualization Issue. Cláudio, Ana Paula; Carmo, Maria Beatriz; Gil, Filipe; Leal, Margarida Mendes // Revista de Ciências da Computação;2011, Vol. 6 Issue 6, p1 

    Most of the time, an observer is not able of processing instantaneously everything that stimulates his senses. Adequate and well-chosen stimuli can produce better results and be processed more quickly. Taking this into account, the aim of our study is to identify graphic symbols that adequately...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics