188 Hits in 3.0 sec

A study of Impact of Integration Structural Context in Multimedia Retrieval: Application on Image Media

Sana Fakhfakh, Mohamed Tmar, Walid Mahdi
2015 Research in Computing Science  
The results show that integration of structural context significantly improves compared results of using a single textual context.  ...  We propose a geometric method who use implicitly of textual and structural context of XML elements and we are particularly interested by improve the effectiveness of various structural factors for multimedia  ...  and 0.2276 for "ImageCLEF 2014" collection) and Minkowski distance (0.2876 for "INEX 2007" collection, 0.2245 for "ImageCLEF 2010" collection and 0.3267 for "ImageCLEF 2014" collection).  ... 
doi:10.13053/rcs-90-1-25 fatcat:qy6jkif3rbgq3cf7v5lvqyqvzi

SINAI at ImageCLEF Wikipedia Retrieval Task 2011: Testing Combined Systems

Miguel Ángel García Cumbreras, Manuel Carlos Díaz-Galiano, Luis Alfonso Ureña López, Javier Arias Buendía
2011 Conference and Labs of the Evaluation Forum  
Several researches demonstrate that the use and integration of various knowledge sources improves the quality and efficiency of information systems.  ...  Using only the English text associated with each image or its translation from French or German, our system applies several combinations of the textual tags and the combination of information retrieval  ...  -The combination of both IR systems with caption and description tags improves a bit the textual result.  ... 
dblp:conf/clef/CumbrerasDLB11 fatcat:bwud2dycivfifdyw5h4y7molgy

SINAI at ImageCLEF 2009 WikipediaMM Task

Manuel Carlos Díaz-Galiano, María Teresa Martín-Valdivia, Luis Alfonso Ureña López, José M. Perea-Ortega
2009 Conference and Labs of the Evaluation Forum  
We have used the LEMUR toolkit as the Information Retrieval system in our experiments.  ...  Thus, we have generated a new collection expanding with WordNet terms in order to perform the information included in this collection. In addition, we have expanded de queries with WordNet too.  ...  For example, the integration of knowledge through the use of ontologies has been very successful in many systems.  ... 
dblp:conf/clef/Diaz-GalianoMLP09a fatcat:rhly32pznjdmfcwmtms2z2bqzu

Improved medical image modality classification using a combination of visual and textual features

Ivica Dimitrovski, Dragi Kocev, Ivan Kitanovski, Suzana Loskovska, Sašo Džeroski
2015 Computerized Medical Imaging and Graphics  
Improved medical image modality classification using a combination of visual and textual features.  ...  More specifically, we used the modality classification databases from the ImageCLEF competitions in 2011, 2012 and 2013, described by four visual and one textual types of features, and combinations thereof  ...  For the textual information, we used the text surrounding the image and its bag-of-words representation.  ... 
doi:10.1016/j.compmedimag.2014.06.005 pmid:24997992 fatcat:g76syoiwe5fbvnmjxvmnryluvy

Medical Image Retrieval: A Multimodal Approach

Yu Cao, Shawn Steffey, Jianbiao He, Degui Xiao, Cui Tao, Ping Chen, Henning Müller
2014 Cancer Informatics  
Specifically, we first investigate a new extended probabilistic Latent Semantic Analysis model to integrate the visual and textual information from medical images to bridge the semantic gap.  ...  We then develop a new deep Boltzmann machine-based multimodal learning model to learn the joint density model from multimodal information in order to derive the missing modality.  ...  Acknowledgments The authors would like to thank Chyeeka Brown and Huijuan Xu for contributing on part of the system implementation. Author contributions  ... 
doi:10.4137/cin.s14053 pmid:26309389 pmcid:PMC4533857 fatcat:axi6x7234ncwrowi3zs6j7dl7a

SINAI at ImageCLEF 2010 Medical Task

Manuel Carlos Díaz-Galiano, María Teresa Martín-Valdivia, Arturo Montejo-Ráez, Miguel Angel García Cumbreras
2010 Conference and Labs of the Evaluation Forum  
Recent researches demonstrate that the use and integration of several knowledge sources improves the quality and efficiency of information systems.  ...  In this paper, we present the system developed for the ImageCLEF 2010 medical task. We show the effect of using the medical ontology MeSH to expand terms found in textual queries.  ...  The efficient access to multimodal information is becoming more and more difficult every day. For this reason, it is necessary to develop search strategies for easier retrieval of useful information.  ... 
dblp:conf/clef/Diaz-GalianoMRC10 fatcat:wfemacngm5f6lme7gco3o26lqa

TELECOM ParisTech at ImageCLEF 2010 Photo Annotation Task: Combining Tags and Visual Features for Learning-Based Image Annotation

Hichem Sahbi, Xi Li
2010 Conference and Labs of the Evaluation Forum  
An image collection is supplied with tags which are used both for training and testing.  ...  In this paper, we describe the participation of TELECOM ParisTech in the ImageCLEF 2010 Photo Annotation challenge.  ...  The model uses the keywords shared by similar images to annotate new ones. In [22] , the similarity measure between images integrates contextual information for concept propagation.  ... 
dblp:conf/clef/SahbiL10 fatcat:whbokooqf5hdnf63zdjw2fkanq

Evaluation axes for medical image retrieval systems

Henning Müller, Paul Clough, William Hersh, Thomas Deselaers, Thomas Lehmann, Antoine Geissbuhler
2005 Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05  
Final goal with most impact will be the use as a diagnostic aid in a real-world clinical setting.  ...  Other applications of image retrieval and image classification can be the automatic annotation of images with basic concepts or the control of DICOM header information.  ...  This is a fairly realistic task that can be used to obtain knowledge about collections that have not been annotated at all.  ... 
doi:10.1145/1101149.1101358 dblp:conf/mm/MullerCHDLG05 fatcat:7vlmcfv7pbgezkan7it57uk5za

Improving Retrieval Using External Annotations: OHSU at ImageCLEF 2010

Steven Bedrick, Jayashree Kalpathy-Cramer
2010 Conference and Labs of the Evaluation Forum  
Over the past several years, our team has focused its efforts on improving retrieval precision performance by mixing visual and textual information.  ...  This year, we chose to explore ways in which we could use external data to enrich our retrieval system's data set; specifically, we annotated each image in the test collection with a set of MeSH headings  ...  Acknowledgements We acknowledge the National Library of Medicine grant 3T15LM007088 for supporting this work, as well as 1K99LM009889.  ... 
dblp:conf/clef/BedrickK10 fatcat:pu6jqzdsnvfulgzejyivkfuj64

Multimodal Photo Retrieval through Finding Similar Documents Enhanced with Visual Clues - a Baseline Method

Bartosz Broda, Mariusz Paradowski, Halina Kwasnicka
2009 Conference and Labs of the Evaluation Forum  
In this paper we present a staring point of our research, connected to a joint Polish-Singaporean research project, titled: Framework for Visual Information Retrieval and Building Content-based Visual  ...  First we extract textual features for each image in the collection and than we use similarity measure to compare pairs of images.  ...  After initial processing of textual data, visual data is used to refine the results presented to user. There is a plethora of methods for textual information retrieval [10] .  ... 
dblp:conf/clef/BrodaPK09 fatcat:7lb4tw5zdbho5cx5xpw3enfa3e

IRIT at ImageCLEF 2010: Medical Retrieval Track

Duy Dinh, Lynda Tamine
2010 Conference and Labs of the Evaluation Forum  
Our information retrieval approach integrates a hybrid method of concept extraction for enhancing the semantics of the document as well as of the query.  ...  The experiments carried out on the Image-CLEF 2010 show that our information retrieval approach based on the proposed method of concept extraction show an improvement of 7.07% in terms of MAP (for the  ...  , using visual features and/or textual features.  ... 
dblp:conf/clef/DinhT10 fatcat:gmal3x6fqjfnnkbod2y2tr3oxy

Overview of the CLEF 2009 Medical Image Retrieval Track [chapter]

Henning Müller, Jayashree Kalpathy–Cramer, Ivan Eggel, Steven Bedrick, Saïd Radhouani, Brian Bakke, Charles E. Kahn, William Hersh
2010 Lecture Notes in Computer Science  
2009 was the sixth year for the ImageCLEF medical retrieval task.  ...  An article's PMID could be used to obtain the officially assigned MeSH (Medical Subject Headings) terms. The collection was entirely in English.  ...  We would like to thank the RSNA for supplying the images of their journals Radiology and Radiographics for the ImageCLEF campaign.  ... 
doi:10.1007/978-3-642-15751-6_8 fatcat:abrmk3557nbbdhams4trskydl4

Multimodal Image Retrieval over a Large Database [chapter]

Débora Myoupo, Adrian Popescu, Hervé Le Borgne, Pierre-Alain Moëllic
2010 Lecture Notes in Computer Science  
Textual queries are reformulated using Wikipedia knowledge and results are then reordered using a k-NN based reranking method.  ...  We compare textual and multimodal retrieval and show that introducing visual reranking results in a significant improvement of performance.  ...  We thank the DGCIS for funding us through the regional business cluster Systematic (project POPS) and Cap Digital (project Mediatic and Romeo), and the french National Agency for Research (ANR) project  ... 
doi:10.1007/978-3-642-15751-6_20 fatcat:4aowzdwztrbaphhrbgudfyyksy

CNRS - TELECOM ParisTech at ImageCLEF 2013 Scalable Concept Image Annotation Task: Winning Annotations with Context Dependent SVMs

Hichem Sahbi
2013 Conference and Labs of the Evaluation Forum  
This edition promotes the use of many contextual cues attached to visual contents. Image collections are supplied with visual features as well as tags taken from different sources (web pages, etc.).  ...  In this paper, we describe the participation of CNRS TELE-COM ParisTech in the ImageCLEF 2013 Scalable Concept Image Annotation challenge.  ...  ); the novel part of this work aims to integrate context (from the ImageCLEF 2013 collection), in kernel design for classification and annotation, and plug these kernels in support vector machines in order  ... 
dblp:conf/clef/Sahbi13 fatcat:3rknf45zwbbe5dsnbwsmpcgo4q

The MedGIFT Project: Global Perspectives of a Medical Doctor

2007 Medical Imaging Technology  
To address this demand, content-based image retrieval (CBIR) has been proposed for a long time with many systems being built to meet several application demands.  ...  Acknowledgement This work was partially supported by the Swiss National Science Foundation (FNS) with grant 205321-109, by the Swiss confederation through a scholarship for Dr.  ...  Whereas for textual IR and natural language processing much research has already improved the understanding and shortcomings, visual medical information retrieval is still in its infancy and needs more  ... 
doi:10.11409/mit.25.356 fatcat:jk7zzyejpzgrjj36pgkr2obs3y
« Previous Showing results 1 — 15 out of 188 results