Content-based Image Retrieval for Scientific Literature Access

Deserno, Thomas M.; Long, L. Rodney

doi:10.3414/me0561

Cited by 20 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides text-based access 6 also content-based access to the medical literature and its figures has been proposed several times. 7,8 To increase the quality of image retrieval of journal figures, automatic modality classification and filtering of retrieval results has been shown to be effective. 9 Compound figures represent about 50% of the figures in the biomedical open access literature used for the ImageCLEF * benchmark.…”

Section: Introductionmentioning

confidence: 99%

Separating compound figures in journal articles to allow for subfigure classification

Chhatkuli

Foncubierta–Rodríguez

Markonis

et al. 2013

SPIE Proceedings

View full text Add to dashboard Cite

Journal images represent an important part of the knowledge stored in the medical literature. Figure classification has received much attention as the information of the image types can be used in a variety of contexts to focus image search and filter out unwanted information or "noise", for example non-clinical images. A major problem in figure classification is the fact that many figures in the biomedical literature are compound figures and do often contain more than a single figure type. Some journals do separate compound figures into several parts but many do not, thus requiring currently manual separation.In this work, a technique of compound figure separation is proposed and implemented based on systematic detection and analysis of uniform space gaps. The method discussed in this article is evaluated on a dataset of journal figures of the open access literature that was created for the ImageCLEF 2012 benchmark and contains about 3000 compound figures.Automatic tools can easily reach a relatively high accuracy in separating compound figures. To further increase accuracy efforts are needed to improve the detection process as well as to avoid over-separation with powerful analysis strategies. The tools of this article have also been tested on a database of approximately 150'000 compound figures from the biomedical literature, making these images available as separate figures for further image analysis and allowing to filter important information from them.

show abstract

Section: Introductionmentioning

confidence: 99%

Separating compound figures in journal articles to allow for subfigure classification

Chhatkuli

Foncubierta–Rodríguez

Markonis

et al. 2013

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…There were also publications in other traditional areas of medical informatics such as knowledgebased decision support [23] or biomedical signal [24] and image [25] processing. Other publications dealt with ontologies [26] or with the analysis [27] and retrieval [28] of certain documents from medicine and health care.…”

Section: Examples From Recent Publicationsmentioning

confidence: 99%

“…[28] uses document retrieval methodology combined with imaging methodology (both are within the field of medical informatics, however within different areas). [34] is very close to biomedical engineering.…”

Section: Examples From Recent Publicationsmentioning

confidence: 99%

Methods in Year 50: Preserving the Past and Preparing for the Future

Haux

Aronsky²,

Leong³

et al. 2011

Methods Inf Med

View full text Add to dashboard Cite

SummaryBackground: Founded in 1962 and, therefore, the oldest international journal in medical informatics, Methods of Information in Medicine will publish its 50th volume in 2011. At the start of the journal's sixth decade, a discussion on the journal's profile seems appropriate. Objectives: To report on the new opportunities for online access to Methods publications as well as on the recent strategic decisions regarding the journal's aims and editorial policies. Methods: Describing and analyzing the journal's aims and scope. Reflecting on recent publications and on the journal's development during the last decade.

show abstract

“…The CLEF med 2009 [28] is a medical dataset containing more than 15 K images, in which 1000 images of 12 classes are selected manually. The following are the details of the 12 classes: …”

Section: Clef Med2009 Database (Db1)mentioning

confidence: 99%

“…The performance of the proposed PE-VQ method is evaluated using three test databases, namely, CLEF med 2009 database (DB1) [28], Corel database (DB2) [29] and standard test images database (DB3) [30] in terms of CR and peak signal-to-noise ratio (PSNR) [31] values. These results are compared with those obtained by the existing algorithms, namely, IP-VQ method [12], JPEG2000 method [32], singular value decomposition and wave difference reduction (SVD & WDR) method [33].…”

Section: Database Descriptionmentioning

confidence: 99%

Lossy image compression based on prediction error and vector quantisation

Ayoobkhan

Eswaran

Ramakrishnan

2017

J Image Video Proc.

View full text Add to dashboard Cite

Lossy image compression has been gaining importance in recent years due to the enormous increase in the volume of image data employed for Internet and other applications. In a lossy compression, it is essential to ensure that the compression process does not affect the quality of the image adversely. The performance of a lossy compression algorithm is evaluated based on two conflicting parameters, namely, compression ratio and image quality which is usually measured by PSNR values. In this paper, a new lossy compression method denoted as PE-VQ method is proposed which employs prediction error and vector quantization (VQ) concepts. An optimum codebook is generated by using a combination of two algorithms, namely, artificial bee colony and genetic algorithms. The performance of the proposed PE-VQ method is evaluated in terms of compression ratio (CR) and PSNR values using three different types of databases, namely, CLEF med 2009, Corel 1 k and standard images (Lena, Barbara etc.). Experiments are conducted for different codebook sizes and for different CR values. The results show that for a given CR, the proposed PE-VQ technique yields higher PSNR value compared to the existing algorithms. It is also shown that higher PSNR values can be obtained by applying VQ on prediction errors rather than on the original image pixels.

show abstract

Content-based Image Retrieval for Scientific Literature Access

Abstract: Therefore, CBIR potentially has a high impact in medical literature search and retrieval.

Cited by 20 publications

References 34 publications

Separating compound figures in journal articles to allow for subfigure classification

Separating compound figures in journal articles to allow for subfigure classification

Methods in Year 50: Preserving the Past and Preparing for the Future

Lossy image compression based on prediction error and vector quantisation

Contact Info

Product

Resources

About