Using Ontologies to Reduce the Semantic Gap between Historians and Image Processing Algorithms

Coustaty, Mickaël; Bouju, Alain; Bertet, Karell; Louis, Georges

doi:10.1109/icdar.2011.40

Cited by 5 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One can find examples of this approach in the Object Ontology of Mezaris et al [30], where the "position" concept represents the position of an area in the image. Many real application studies included an a priori spatial information in their image analysis process [34,22,13,10].…”

Section: Narrowing the Semantic Gapmentioning

confidence: 99%

See 1 more Smart Citation

An ontology-based framework for the automated analysis and interpretation of comic books’ images

Guerin

Rigaud

Bertet

et al. 2017

Information Sciences

Self Cite

View full text Add to dashboard Cite

Since the beginning of the twenty-first century, the cultural industry has been through a massive and historical mutation induced by the rise of digital technologies. The comic books industry keeps looking for the right solution and has not yet produced anything as convincing as the music or movie have. A lot of energy has been spent to transfer printed material to digital supports so far. The specificities of those supports are not always exploited at the best of their capabilities, while they could potentially be used to create new reading conventions. In spite of the needs induced by the large amount of data created since the beginning of the comics history, content indexing has been left behind. It is indeed quite a challenge to index such a composition of textual and visual information. While a growing number of researchers are working on comic books' image analysis from a low-level point of view, only a few are tackling the issue of representing the content at a high semantic level. We propose in this article a framework to handle the content of a comic book, to support the automatic extraction of its visual components and to formalize the semantic of the domain's codes. We tested our framework over two applications: 1) the unsupervised content discovery of comic books' images, 2) its capabilities to handle complex layouts and to produce a respectful browsing experience to the digital comics reader.

show abstract

Section: Narrowing the Semantic Gapmentioning

confidence: 99%

“…The ontology used in [13], to analyze images of dropped initials, formalizes the conditions for an extracted region to be identified as a letter. A SWRL rule translates the fact that a letter is the biggest area, with a limited amount of holes in its shape, centered in the image into a classification inference operation.…”

Section: Narrowing the Semantic Gapmentioning

confidence: 99%

An ontology-based framework for the automated analysis and interpretation of comic books’ images

Guerin

Rigaud

Bertet

et al. 2017

Information Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…The idea is to add semantic knowledge to improve the assistance given by these environments in order to support the development and the maintenance of software. Another example is the work of Coustaty et al (2011). In fact, they integrate ontologies in image processing algorithms in order to detect their semantics.…”

Section: Ijicc 92mentioning

confidence: 99%

Exogenous approach to improve topic segmentation

Naili

Chaïbi

Ghezala

2016

International Journal of Intelligent Computing and Cybernetics

View full text Add to dashboard Cite

Purpose – Topic segmentation is one of the active research fields in natural language processing. Also, many topic segmenters have been proposed. However, the current challenge of researchers is the improvement of these segmenters by using external resources. Therefore, the purpose of this paper is to integrate study and evaluate a new external semantic resource in topic segmentation. Design/methodology/approach – New topic segmenters (TSS-Onto and TSB-Onto) are proposed based on the two well-known segmenters C99 and TextTiling. The proposed segmenters integrate semantic knowledge to the segmentation process by using a domain ontology as an external resource. Subsequently, an evaluation is made to study the effect of this resource on the quality of topic segmentation along with a comparative study with related works. Findings – Based on this study, the authors showed that adding semantic knowledge, which is extracted from a domain ontology, improves the quality of topic segmentation. Moreover, TSS-Ont outperforms TSB-Ont in terms of quality of topic segmentation. Research limitations/implications – The main limitation of this study is the used test corpus for the evaluation which is not a benchmark. However, we used a collection of scientific papers from well-known digital libraries (ArXiv and ACM). Practical implications – The proposed topic segmenters can be useful in different NLP applications such as information retrieval and text summarizing. Originality/value – The primary original contribution of this paper is the improvement of topic segmentation based on semantic knowledge. This knowledge is extracted from an ontological external resource.

show abstract

“…In addition, shapes obtained are cleaned, allowing us to abstain from the noise, what offers greater robustness for segmentation and description. This decomposition gives us simplified images and particularly we have worked on shapes' layer to extract most significant shapes like the letter or faces [6], arms, legs [5], etc. All these elements are useful for historians to retrieve similar images by content.…”

Section: Simplifying Drop Capsmentioning

confidence: 99%

Ancient Documents Denoising and Decomposition Using Aujol and Chambolle Algorithm

Coustaty

Dubois

Ménard

et al. 2013

Graphics Recognition. New Trends and Challenges

View full text Add to dashboard Cite

With the improvement of printing technology since the 15th century, there is a huge amount of printed documents published and distributed. These documents are degraded by the time and require to be preprocessed before being submitted to image indexing strategy, in order to enhance the quality of images. This paper proposes a new pre-processing that permits to denoise these documents, by using a Aujol and Chambolle algorithm. Aujol and Chambolle algorithm allows to extract meaningful components from image. In this case, we can extract shapes, textures and noise. Some examples of specific processings applied on each layer are illustrated in this paper

show abstract

Using Ontologies to Reduce the Semantic Gap between Historians and Image Processing Algorithms

Cited by 5 publications

References 8 publications

An ontology-based framework for the automated analysis and interpretation of comic books’ images

An ontology-based framework for the automated analysis and interpretation of comic books’ images

Exogenous approach to improve topic segmentation

Ancient Documents Denoising and Decomposition Using Aujol and Chambolle Algorithm

Contact Info

Product

Resources

About