Using Fuzzy DLs to Enhance Semantic Image Analysis

Research in image analysis has reached a point where detectors can be learned in a generic fashion for a significant number of conceptual entities. The obtained performance however exhibits versatile behaviour, reflecting implications over the training set selection, similarities in visual manifestations of distinct conceptual entities, and appearance variations of the conceptual entities. In this paper, we investigate the use of formal semantics in order to benefit from the logical associations between the conceptual entities, and thereby alleviate part of the challenges involved in extracting semantic descriptions. More specifically, a fuzzy DL based reasoning framework is proposed for the extraction of enhanced image descriptions based on an initial set of graded annotations, generated through generic image analysis techniques. Under the proposed reasoning framework, the initial descriptions are integrated and further enriched at a semantic level, while additionally inconsistencies emanating from conflicting descriptions are resolved. Experimentation in the domain of outdoor images has shown very promising results, demonstrating the added value in terms of accuracy and completeness of the resulting content descriptions.

[1]  Frank van Harmelen,et al.  A Framework for Handling Inconsistency in Changing Ontologies , 2005, SEMWEB.

[2]  Trevor P Martin.  Fuzzy Logic and the Semantic Web , 2005, Capturing Intelligence.

[3]  Yannis Avrithis,et al.  Towards Semantic Multimedia Indexing by Classification & Reasoning on Textual Metadata , 2007, KAMC.

[4]  Diego Calvanese,et al.  The Description Logic Handbook: Theory, Implementation, and Applications , 2003, Description Logic Handbook.

[5]  Jane Hunter,et al.  Rules-By-Example - A Novel Approach to Semantic Indexing and Querying of Images , 2004, SEMWEB.

[6]  H. Hellwagner,et al.  2nd International Workshop on Semantic Media Adaptation and Personalization , 2006, 2006 First International Workshop on Semantic Media Adaptation and Personalization (SMAP'06).

[7]  Philipp Cimiano,et al.  Corpus-based Pattern Induction for a Knowledge-based Question Answering Approach , 2007 .

[8]  Ramesh C. Jain,et al.  Knowledge representation and control in computer vision systems , 1988, IEEE Expert.

[9]  Umberto Straccia,et al.  DLMedia: an Ontology Mediated Multimedia Information Retrieval System , 2007, Description Logics.

[10]  Bruce A. Draper,et al.  Knowledge-directed vision: control, learning, and integration , 1996, Proc. IEEE.

[11]  Michael G. Strintzis,et al.  Knowledge-assisted semantic video object detection , 2005, IEEE Transactions on Circuits and Systems for Video Technology.

[12]  Umberto Straccia,et al.  A fuzzy description logic for the semantic web , 2006, Fuzzy Logic and the Semantic Web.

[13]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Stefanos Kollias,et al.  Multimedia Reasoning with f-SHIN , 2007 .

[15]  Jeff Z. Pan,et al.  Handling Imprecise Knowledge with Fuzzy Description Logic , 2006, Description Logics.

[16]  Alberto Del Bimbo,et al.  Semantic annotation and retrieval of video events using multimedia ontologies , 2007, International Conference on Semantic Computing (ICSC 2007).

[17]  Jane Hunter,et al.  Evaluating the application of semantic inferencing rules to image annotation , 2005, K-CAP '05.

[18]  Umberto Straccia,et al.  Transforming Fuzzy Description Logics into Classical Description Logics , 2004, JELIA.

[19]  John C. Miles,et al.  Knowledge Representation and Control , 1994 .

[20]  Günther Palm,et al.  KI 2004: Advances in Artificial Intelligence , 2004, Lecture Notes in Computer Science.

[21]  Bernd Neumann,et al.  On scene interpretation with description logics , 2006, Image Vis. Comput..

[22]  Steffen Staab,et al.  Knowledge representation and semantic annotation of multimedia content , 2006 .

[23]  Otthein Herzog,et al.  Content-based Image Retrieval by Ontology-based Object Recognition , 2004 .

[24]  Umberto Straccia,et al.  Reasoning within Fuzzy Description Logics , 2011, J. Artif. Intell. Res..

[25]  Frédéric Jurie,et al.  Fast Discriminative Visual Codebooks using Randomized Clustering Forests , 2006, NIPS.

[26]  R. Moller,et al.  Towards computer vision with description logics: some recent progress , 1999, Proceedings Integration of Speech and Image Understanding.

[27]  Noel E. O'Connor,et al.  Learning Midlevel Image Features for Natural Scene and Texture Classification , 2007, IEEE Transactions on Circuits and Systems for Video Technology.

[28]  Bijan Parsia,et al.  Repairing Unsatisfiable Concepts in OWL Ontologies , 2006, ESWC.

[29]  Michael G. Strintzis,et al.  Multimedia Reasoning with Natural Language Support , 2007 .

[30]  Gerald Friedland.  Current Multimedia Data Formats and Semantic Computing: A Practical Example and the Challenges for the Future , 2007 .

[31]  R. Möller,et al.  Multimedia Interpretation as Abduction , 2007 .

[32]  S. McKie.  Scriptclud.com: Content Clouds for Screenplays , 2007 .

[33]  Ian Horrocks,et al.  The Fuzzy Description Logic f-SHIN , 2005, ISWC-URSW.