Shape Indexing and Retrieval: A Hybrid Approach Using Ontological Descriptions

This paper presents a novel hybrid approach for visual information retrieval (VIR) that combines shape analysis of objects in image with their indexing by textual descriptions. The principal goal of presented technique is applying Two Segments Turning Function (2STF) proposed by authors for efficient invariant to spatial variations shape processing and implementation of semantic Web approaches for ontology-based user-oriented annotations of multimedia information. In the proposed approach the user’s textual queries are converted to image features, which are used for images searching, indexing, interpretation, and retrieval. A decision about similarity between retrieved image and user’s query is taken computing the shape convergence to 2STF combining it with matching the ontological annotations of objects in image and providing in this way automatic definition of the machine-understandable semantics. In order to evaluate the proposed approach the Image Retrieval by Ontological Description of Shapes system has been designed and tested using some standard image domains.

[1]  Farzin Mokhtarian,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Oleg Starostenko,et al.  CONTENT BASED VISUAL INFORMATION RETRIEVAL FOR MANAGEMENT INFORMATION SYSTEMS , 2007 .

[3]  Esther M. Arkin,et al.  An efficiently computable metric for comparing polygonal shapes , 1991, SODA '90.

[4]  Alberto Del Bimbo,et al.  Visual Image Retrieval by Elastic Matching of User Sketches , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Michael S. Lew,et al.  Principles of Visual Information Retrieval , 2001, Advances in Pattern Recognition.

[6]  Dieter Fensel,et al.  Ontologies: A silver bullet for knowledge management and electronic commerce , 2002 .

[7]  Thomas R. Gruber,et al.  A translation approach to portable ontology specifications , 1993 .

[8]  Aljoscha Smolic,et al.  A set of visual feature descriptors and their combination in a low-level description scheme , 2000, Signal Process. Image Commun..

[9]  Nicola Guarino,et al.  Semantic Matching: Formal Ontological Distinctions for Information Organization, Extraction, and Integration , 1997, SCIE.

[10]  Oleg Starostenko,et al.  A Novel Star Field Approach for Shape Indexing in CBIR Systems , 2007, Eng. Lett..

[11]  David Beckett.  The design and implementation of the Redland RDF application framework , 2002, Comput. Networks.

[12]  Oleg Starostenko,et al.  A Novel Shape and Ontological Indexing for VIR Systems , 2006, AMCIS.

[13]  Mauricio Osorio,et al.  Logics with Common Weak Completions , 2006, J. Log. Comput..

[14]  Arnold W. M. Smeulders,et al.  PicToSeek: combining color and shape invariant features for image retrieval , 2000, IEEE Trans. Image Process..

[15]  Oleg Starostenko,et al.  A Hybrid Approach for Image Retrieval with Ontological Content-Based Indexing , 2005, CIARP.

[16]  Antonio Badia,et al.  Ontologies , 2001, Springer Berlin Heidelberg.