Results 1 - 10
of
62
Overview of the ImageCLEFmed 2006 medical retrieval and annotation tasks
- In: CLEF 2006 Proceedings. Lecture Notes in Computer Science (2007
, 2006
"... Abstract. This paper describes the medical image retrieval and annotation tasks of ImageCLEF 2006. Both tasks are described with respect to goals, databases, topics, results, and techniques. The ImageCLEFmed retrieval task had 12 participating groups (100 runs). Most runs were automatic, with only a ..."
Abstract
-
Cited by 43 (13 self)
- Add to MetaCart
(Show Context)
Abstract. This paper describes the medical image retrieval and annotation tasks of ImageCLEF 2006. Both tasks are described with respect to goals, databases, topics, results, and techniques. The ImageCLEFmed retrieval task had 12 participating groups (100 runs). Most runs were automatic, with only a few manual or interactive. Purely textual runs were in the majority compared to purely visual runs but most were mixed, using visual and textual information. None of the manual or interactive techniques were significantly better than automatic runs. The best– performing systems used visual and textual techniques combined, but combinations of visual and textual features often did not improve performance. Purely visual systems only performed well on visual topics. The medical automatic annotation used a larger database of 10,000 training images from 116 classes, up from 9,000 images from 57 classes in 2005. Twelve groups submitted 28 runs. Despite the larger number of classes, results were almost as good as in 2005 which demonstrates a clear improvement in performance. The best system of 2005 would have received a position in the middle in 2006.
H.: Overview of the ImageCLEF 2006 photographic retrieval and object annotation tasks
- In: Proceedings of the CLEF 2006 workshop
, 2006
"... This paper describes the general photographic retrieval and object annotation tasks of the ImageCLEF 2006 evaluation campaign. These tasks provide both the resources and the framework necessary to perform comparative laboratory-style evaluation of visual information systems for image retrieval and a ..."
Abstract
-
Cited by 24 (7 self)
- Add to MetaCart
(Show Context)
This paper describes the general photographic retrieval and object annotation tasks of the ImageCLEF 2006 evaluation campaign. These tasks provide both the resources and the framework necessary to perform comparative laboratory-style evaluation of visual information systems for image retrieval and automatic image annotation. Both tasks offer something new for 2006 and attracted a large number of submissions: 12 groups participating in ImageCLEFphoto and 3 in the automatic annotation task. This paper summarises components used in the benchmark, including the collections, the search and annotation tasks, the submissions from participating groups, and results. The general photographic retrieval task, ImageCLEFphoto, used a new collection – the IAPR-TC12 Benchmark – of 20,000 colour photographs with semi-structured captions in English and German. This new collection replaces the St Andrews collection of historic photographs used for the previous three years. For ImageCLEFphoto groups submitted mainly text-only runs. However, 31 % of runs involved some kind of visual retrieval technique, typically combined with text through the merging of image and
The CLEF 2004 Cross Language Image Retrieval Track
- EDS.) MULTILINGUAL INFORMATION ACCESS FOR TEXT, SPEECH AND IMAGES: RESULTS OF THE FIFTH CLEF EVALUATION CAMPAIGN, LECTURE NOTES IN COMPUTER SCIENCE
, 2005
"... The purpose of this paper is to outline efforts from the 2004 CLEF cross–language image retrieval campaign (ImageCLEF). The aim of this CLEF track is to explore the use of both text and content–based retrieval methods for cross–language image retrieval. Three tasks were offered in the ImageCLEF tra ..."
Abstract
-
Cited by 23 (9 self)
- Add to MetaCart
(Show Context)
The purpose of this paper is to outline efforts from the 2004 CLEF cross–language image retrieval campaign (ImageCLEF). The aim of this CLEF track is to explore the use of both text and content–based retrieval methods for cross–language image retrieval. Three tasks were offered in the ImageCLEF track: a TREC–style ad-hoc retrieval task, retrieval from a medical collection, and a user–centered (interactive) evaluation task. Eighteen research groups from a variety of backgrounds and nationalities participated in ImageCLEF. In this paper we describe the ImageCLEF tasks, submissions from participating groups and summarise the main findings.
Fire – flexible image retrieval engine: Imageclef 2004 evaluation
- In Proceeding of Multilingual Information Access for Text, Speech and Images – Fifth Workshop of the Cross-Language Evaluation Forum (CLEF2004), Volume 3491
, 2005
"... Abstract. We describe FIRE, a content-based image retrieval system, and the methods we used within this system in the ImageCLEF 2004 evaluation. In FIRE, various features are available to represent images. The diversity of available features allows the user to adapt the system to the task at hand. A ..."
Abstract
-
Cited by 22 (2 self)
- Add to MetaCart
(Show Context)
Abstract. We describe FIRE, a content-based image retrieval system, and the methods we used within this system in the ImageCLEF 2004 evaluation. In FIRE, various features are available to represent images. The diversity of available features allows the user to adapt the system to the task at hand. A weighted combination of features admits flexible query formulations and helps with processing specific queries. For the ImageCLEF 2004 evaluation, we used the image content alone and obtained the best result in the category “only visual features, fully automatic retrieval ” in the medical retrieval task. Additionally, the results compare favorably to other systems, even if they make use of the textual information in addition to the images. 1
2007a. Overview of the ImageCLEFmed 2007 medical retrieval and annotation tasks. In: Working notes of the CLEF 2007 Workshop
"... Abstract. This paper describes the medical image retrieval and medical image annotation tasks of ImageCLEF 2007. Separate sections describe each of the two tasks, with the participation and an evaluation of major findings from the results of each given. A total of 13 groups participated in the medic ..."
Abstract
-
Cited by 20 (7 self)
- Add to MetaCart
(Show Context)
Abstract. This paper describes the medical image retrieval and medical image annotation tasks of ImageCLEF 2007. Separate sections describe each of the two tasks, with the participation and an evaluation of major findings from the results of each given. A total of 13 groups participated in the medical retrieval task and 10 in the medical annotation task. The medical retrieval task added two new data sets for a total of over 66’000 images. Topics were derived from a log file of the Pubmed biomedical literature search system, creating realistic information needs with a clear user model. The medical annotation task was in 2007 organized in a new format as a hierarchical classification had to be performed and classification could be stopped at any hierarchy level. This required algorithms to change significantly and to integrate a confidence level into their decisions to be able to judge where to stop classification to avoid making mistakes in the hierarchy. Scoring took into account errors and unclassified parts. 1
Fractional distance measures for content-based image retrieval
- In 27th European Conference on Information Retrieval
, 2005
"... Abstract. We have applied the concept of fractional distance measures, proposed by Aggarwal et al. [1], to content-based image retrieval. Our experiments show that retrieval performances of these measures consistently outperform the more usual Manhattan and Euclidean distance metrics when used with ..."
Abstract
-
Cited by 20 (7 self)
- Add to MetaCart
(Show Context)
Abstract. We have applied the concept of fractional distance measures, proposed by Aggarwal et al. [1], to content-based image retrieval. Our experiments show that retrieval performances of these measures consistently outperform the more usual Manhattan and Euclidean distance metrics when used with a wide range of high-dimensional visual features. We used the parameters learnt from a Corel dataset on a variety of different collections, including the TRECVID 2003 and ImageCLEF 2004 datasets. We found that the specific optimum parameters varied but the general performance increase was consistent across all 3 collections. To squeeze the last bit of performance out of a system it would be necessary to train a distance measure for a specific collection. However, a fractional distance measure with parameter p =0.5 will consistently outperform both L1 and L2 norms. 1
The NN k technique for image searching and browsing
, 2005
"... Retrieval of images from large image archives based solely on their visual similarity to a query image provides an exciting alternative to conventional text-based search. For content-based retrieval images are represented in terms of visual features. The question of how to combine these for similari ..."
Abstract
-
Cited by 11 (6 self)
- Add to MetaCart
(Show Context)
Retrieval of images from large image archives based solely on their visual similarity to a query image provides an exciting alternative to conventional text-based search. For content-based retrieval images are represented in terms of visual features. The question of how to combine these for similarity computation is typically addressed by eliciting relevance feedback from the user on the retrieved images. We argue in this thesis that the prevailing approach to relevance feedback suffers from three significant shortcomings: firstly, it leaves unsolved the question of how to combine features for the first retrieval; secondly, the advantage of automated content-extraction over manual annotation is greatest for large collections but if the query image is not constrained to come from the indexed collection, content-based retrieval entails imagewise comparisons leading to prohibitive response times; thirdly, users may only have vaguely defined information needs or may change their needs in the course of the interaction. The large majority of relevance feedback techniques are ill-suited for such undirected exploration. We propose a new framework of user interaction that addresses these limitations. It is centred on what we call the NN k idea. The NN k of an image are all those images that are most similar to it under some combination of features. They can be viewed as representatives of the possible
Overview of the CLEF 2010 medical image retrieval track
"... Abstract. The seventh edition of the ImageCLEF medical retrieval task ..."
Abstract
-
Cited by 11 (0 self)
- Add to MetaCart
Abstract. The seventh edition of the ImageCLEF medical retrieval task
Vismed: a visual vocabulary approach for medical image indexing and retrieval
- In Proceedings of the Asia Information Retrieval Symposium
, 2005
"... Abstract. Voluminous medical images are generated daily. They are critical assets for medical diagnosis, research, and teaching. To facilitate automatic indexing and retrieval of large medical image databases, we propose a structured framework for designing and learning vocabularies of meaningful me ..."
Abstract
-
Cited by 9 (8 self)
- Add to MetaCart
(Show Context)
Abstract. Voluminous medical images are generated daily. They are critical assets for medical diagnosis, research, and teaching. To facilitate automatic indexing and retrieval of large medical image databases, we propose a structured framework for designing and learning vocabularies of meaningful medical terms associated with visual appearance from image samples. These VisMed terms span a new feature space to represent medical image contents. After a multi-scale detection process, a medical image is indexed as compact spatial distributions of VisMed terms. A flexible tiling (FlexiTile) matching scheme is proposed to compare the similarity between two medical images of arbitrary aspect ratios. We evaluate the VisMed approach on the medical retrieval task of the ImageCLEF 2004 benchmark. Based on 2 % of the 8725 CasImage collection, we cropped 1170 image regions to train and validate 40 VisMed terms using support vector machines. The Mean Average Precision (MAP) over 26 query topics is 0.4156, an improvement over all the automatic runs in ImageCLEF 2004. 1
queries on the CasImage database within the IRMA framework
- Lecture Notes in Computer Science,Springer 3491
, 2005
"... Abstract. Recent research has suggested that there is no general similarity measure, which can be applied on arbitrary databases without any parameterization. Hence, the optimal combination of similarity measures and parameters must be identified for each new image repository. This optimization loop ..."
Abstract
-
Cited by 9 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Recent research has suggested that there is no general similarity measure, which can be applied on arbitrary databases without any parameterization. Hence, the optimal combination of similarity measures and parameters must be identified for each new image repository. This optimization loop is time consuming and depends on the experience of the designer as well as the knowledge of the medical expert. It would be useful if results that have been obtained for one data set can be transferred to another without extensive re-design. This transfer is vital if content-based image retrieval is integrated into complex environments such as picture archiving and communication systems. The image retrieval in medical applications (IRMA) project defines a framework that strictly separates data administration and application logic. This permits an efficient transfer of the data abstraction of one database on another without re-designing the software. In the ImageCLEF competition, the query performance was evaluated on the CasImage data set without optimization of the feature combination successfully applied to the IRMA corpus. IRMA only makes use of basic features obtained from grey-value representations of the images without additional textual annotations. The results indicate that transfer of parameterization is possible without time consuming parameter adaption and significant loss of retrieval quality. 1
