Image retrieval for information systems

Hermes, Thorsten; Klauck, Christoph; Kreyss, Jutta; Zhang, J.

doi:10.1117/12.205310

Cited by 33 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first is textual representation scheme. Hermes et al 8 use similarity technique to derive the natural language description of a outdoor scene image in the IRIS system. The textual description is generated by four sub-steps: feature extraction like colors, textures, and contours, segmentation, and interpretation of part-whole relations.…”

Section: Related Workmentioning

confidence: 99%

<title>Semantic-based image retrieval by text mining on environmental texts</title>

Yang

Lee

2003

SPIE Proceedings

View full text Add to dashboard Cite

In this paper we propose a novel method to bridge the 'semantic gap' between a user's information need and the image content. The semantic gap describes the major deficiency of content-based image retrieval (CBIR) systems which use visual features extracted from images to describe the images. We conquer the deficiency by extracting semantic of an image from the environmental texts around it. Since an image generally co-exists with accompany texts in various formats, we may rely on such environmental texts to discover the semantic of the image. A text mining approach based on self-organizing maps is used to extract the semantic of an image from its environmental texts. We performed experiments on a small set of images and obtained promising results.

show abstract

Section: Related Workmentioning

confidence: 99%

<title>Semantic-based image retrieval by text mining on environmental texts</title>

Yang

Lee

2003

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…As an alternative approach to image retrieval, we have combined Hyspirit with the IRIS image indexing system (Hermes, Klauck, Keys, & Zhang, 1995) which performs semantic indexing by inferring semantic concepts from syntactic features. IRIS has been applied successfully to the domain of landscape photos, where it detects basic concepts like e.g.…”

Section: Applicationmentioning

confidence: 99%

Probabilistic datalog: Implementing logical information retrieval for advanced applications

Fuhr

2000

J. Am. Soc. Info. Sci.

View full text Add to dashboard Cite

In the logical approach to information retrieval (IR), retrieval is considered as uncertain inference. Whereas classical IR models are based on propositional logic, we combine Datalog (function‐free Horn clause predicate logic) with probability theory. Therefore, probabilistic weights may be attached to both facts and rules. The underlying semantics extends the well‐founded semantics of modularly stratified Datalog to a possible worlds semantics. By using default independence assumptions with explicit specification of disjoint events, the inference process always yields point probabilities. We describe an evaluation method and present an implementation. This approach allows for easy formulation of specific retrieval models for arbitrary applications, and classical probabilistic IR models can be implemented by specifying the appropriate rules. In comparison to other approaches, the possibility of recursive rules allows for more powerful inferences, and predicate logic gives the expressiveness required for multimedia retrieval. Furthermore, probabilistic Datalog can be used as a query language for integrated information retrieval and database systems.

show abstract

“…To enable the use of image analysis results for more than similarity search, they must be semantically interpreted. This can be accomplished through model-based object recognition (e.g., Hermes et al 1995), which allows the identification of specific objects. The modeling effort is high and only justifiable in special cases, e.g., when the information needs of users can be precisely described a priori (e.g., police tasks, cf.…”

Section: Image Retrieval Based On Feature Analysis and Conceptual Reamentioning

confidence: 99%

Can Rule-Based Indexing Support Concept-BasedMultimedia Retrieval in Digital Libraries? Some Experimental Results∗

Thiel

Everts

Lutes

et al. 1999

Electronic Workshops in Computing

View full text Add to dashboard Cite

The emerging conception of a "digital library" as an information environment in which distributed information sources are made available in an integrated way implies new requirements for indexing and retrieval methods. Therefore, one important research topic in the field of digital libraries is the design of task-specific methods for very precise searching. In addition, we have to anticipate highly dynamic information bases which change continually. This paper outlines an approach which addresses both problems. Rule-based indexing can be used to support highly precise searches in dynamic information bases. The method enables users to perform conceptual searches in image collections, thus going far beyond contemporary content-based retrieval methods for pictorial material. The paper concludes with a discussion of the empirical results obtained so far.

show abstract

Image retrieval for information systems

Cited by 33 publications

References 0 publications

<title>Semantic-based image retrieval by text mining on environmental texts</title>

<title>Semantic-based image retrieval by text mining on environmental texts</title>

Probabilistic datalog: Implementing logical information retrieval for advanced applications

Can Rule-Based Indexing Support Concept-BasedMultimedia Retrieval in Digital Libraries? Some Experimental Results∗

Contact Info

Product

Resources

About