A Representation Model of Images Based on Graphs and Automatic Instantiation of Its Skeletal Configuration

Benafia, Ali; Maamri, Ramdane; Sahnoun, Zaïdi; Saadaoui, Sami; Saadna, Yasmina

doi:10.1007/978-3-642-22158-3_24

Cited by 2 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We find in [5] an approach for indexing images by a semantic graph is based on a representation combining several descriptors. This model like the other models is supported by resources of knowledge and terminology needed for future applications of image processing.…”

Section: Peremeter Of the Studymentioning

confidence: 99%

“…Our problematic is this: we already have a model of description of images [5] where the descriptors associated with the images are all non-textual. Is there a way, and how to expand and consolidate these non-textual descriptors of our model with a structure of textual index?…”

Section: Peremeter Of the Studymentioning

confidence: 99%

“…These terms issued from the various legends will constitute a linguistic index for the corpus. This index will be added to the descriptors already defined in the model described in [5] to obtain a global index that includes a typology of descriptors. Our contribution is therefore seeking to combine, in a prototype of automatic indexation, terms extracted from texts describing images with visual and semantic descriptors related to images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Indexing Approach based on a Hybrid Model of Terminology-extraction using a Filtering by Elimination Terms

Benafia¹,

Maamri²,

Sahnoun³

2013

JAIT

View full text Add to dashboard Cite

the extraction of terms is an important step in building a resource for indexing and many powerful tools are available for several languages. This complex process, which identifies candidate terms may become indexes for annotations or documents, is often subject to the problem of lack of relevance of calculated terms. Consequently, the extraction of terminology from the texts must be strong and solid to handle the errors and suggest better results, without encumbering the user with too many proposals of indexes. It is, in this perspective that we propose here a new indexing approach based on a hybrid model of terminologies extraction using a filtering by elimination terms and which operates on a corpus of annotated images with legends .

show abstract

Section: Peremeter Of the Studymentioning

confidence: 99%

Section: Peremeter Of the Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation