Automatic annotation of online articles based on visual feature classification

Burget, Radek; Burgetová, Ivana

doi:10.1504/ijiids.2011.041322

Cited by 2 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ontology classes are based on the class Rectangle with its characteristic size, position and visual features. The used visual features follow the suggestions from article of Burget and Burgetová [3]. Class Border denotes one side border of the particular object.…”

Section: Related Researchmentioning

confidence: 99%

“…The manually assigned classes may be used for training an automatic classifier which is able to assign the classes to new, previously unknown documents automatically. For instance, such approach was presented in [3].…”

Section: Semantic Ontologymentioning

confidence: 99%

“…For mapping the individual document parts to the particular concepts of the domain ontology, different approaches may be used such as an approximate tree mapping [5], visual feature classification [3], Name Entity Recognition (NER) or any combination of these approaches.…”

Section: Domain Ontologymentioning

confidence: 99%

“…For rendering the documents and obtaining the box model, we have used the CSSBox 3 rendering engine. Subsequently, the segmentation model was created from the box model using our page segmentation algorithm based on [3]. The obtained models have been described using the proposed box model ontology and segmentation ontology and stored as the RDF data.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…Recent research shows that the visual information may be useful for many applications such as document indexing [14] or content classification [3]. However, there exists no general document model that would allow to explicitly represent the visual information together with the other mentioned types of information about the document.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Web document description based on ontologies

Milicka

Burget

2013

2013 Second International Conference on Informatics &Amp; Applications (ICIA)

Self Cite

View full text Add to dashboard Cite

The effective document modeling based on the visual features is not always trivial in the case where we want to apply the advance document processing with the visual features reflection. In this paper, we are suggesting a document description based on RDF and ontologies. Such approach allows modeling on several levels of abstraction that is reflecting the document visual features perceived by human. Such approach also advantageously uses the existing tools for the RDF querying and reasoning. The paper presents four levels of the document description where all of them are based on the ontologies but each level represents a different knowledge. The main part of the paper is oriented on the document description based on the Semantic ontology. The ontology is based on SWRL rules where rules assign the elements to a given classes. Finally, we are presenting examples of the class definitions based on the SWRL rules.

show abstract

Section: Related Researchmentioning

confidence: 99%

Section: Semantic Ontologymentioning

confidence: 99%

Section: Domain Ontologymentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Web document description based on ontologies

Milicka

Burget

2013

2013 Second International Conference on Informatics &Amp; Applications (ICIA)

Self Cite

View full text Add to dashboard Cite

show abstract

Extracting Visually Presented Element Relationships from Web Documents

Burget

Smrž

2013

International Journal of Cognitive Informatics and Natural Intelligence

Self Cite

View full text Add to dashboard Cite

Many documents in the World Wide Web present structured information that consists of multiple pieces of data with certain relationships among them. Although it is usually not difficult to identify the individual data values in the document text, their relationships are often not explicitly described in the document content. They are expressed by visual presentation of the document content that is expected to be interpreted by a human reader. In this paper, the authors propose a formal generic model of logical relationships in a document based on an interpretation of visual presentation patterns in the documents. The model describes the visually expressed relationships between individual parts of the contents independently of the document format and the particular way of presentation. Therefore, it can be used as an appropriate document model in many information retrieval or extraction applications. The authors formally define the model, the authors introduce a method of extracting the relationships between the content parts based on the visual presentation analysis and the authors discuss the expected applications. The authors also present a new dataset consisting of programmes of conferences and other scientific events and the authors discuss its suitability for the task in hand. Finally, the authors use the dataset to evaluate results of the implemented system.

show abstract

Automatic annotation of online articles based on visual feature classification

Cited by 2 publications

References 0 publications

Web document description based on ontologies

Web document description based on ontologies

Extracting Visually Presented Element Relationships from Web Documents

Contact Info

Product

Resources

About