Symbol Grounding for Semantic Image Interpretation: From Image Data to Semantics

This paper presents an original approach for the symbol grounding problem involved in semantic image interpretation, i.e. the problem of the mapping between image data and semantic data. Our approach involves the following aspects of cognitive vision : knowledge acquisition and knowledge representation, reasoning and machine learning. The symbol grounding problem is considered as a problem as such and we propose an independent cognitive system dedicated to symbol grounding. This symbol grounding system introduces an intermediate layer between the semantic interpretation problem (reasoning in the semantic level) and the image processing problem. An important aspect of the work concerns the use of two ontologies to make easier the communication between the different layers : a visual concept ontology and an image processing ontology. We use two approaches to solve the symbol grounding problem: a machine learning approach and an a priori knowledge based approach.

[1]  Michael Uschold,et al.  Ontologies: principles, methods and applications , 1996, The Knowledge Engineering Review.

[2]  Takashi Matsuyama,et al.  SIGMA: A Knowledge-Based Aerial Image Understanding System , 1990 .

[3]  Michael G. Strintzis,et al.  Region-Based Image Retrieval Using an Object Ontology and Relevance Feedback , 2004, EURASIP J. Adv. Signal Process..

[4]  Silvia Coradeschi,et al.  Anchoring symbols to sensory data , 1999 .

[5]  Bruce A. Draper,et al.  ISR: a database for symbolic processing in computer vision , 1989, Computer.

[6]  Ying Liu,et al.  Region-Based Image Retrieval with High-Level Semantic Color Names , 2005, 11th International Multimedia Modelling Conference.

[7]  Refractor.  Vision , 2000, The Lancet.

[8]  Monique Thonnat,et al.  Towards ontology-based cognitive vision , 2004, Machine Vision and Applications.

[9]  Gérard Giraudon,et al.  Scene analysis system , 1994, Proceedings of 1st International Conference on Image Processing.

[10]  M. Thonnat.  Knowledge-based techniques for image processing and for image understanding , 2002 .

[11]  Alessandro Saffiotti,et al.  Fuzzy anchoring , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[12]  Peter Gärdenfors,et al.  Conceptual spaces - the geometry of thought , 2000 .

[13]  A. Ravishankar Rao,et al.  The Texture Lexicon: Understanding the Categorization of Visual Texture Terms and Their Relationship to Texture Images , 1997, Cogn. Sci..

[14]  Salvatore Gaglio,et al.  A Cognitive Architecture for Artificial Vision , 1997, Artif. Intell..

[15]  Nozha Boujemaa,et al.  New image retrieval paradigm: logical composition of region categories , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[16]  Monique Thonnat,et al.  A Weakly Supervised Approach for Semantic Image Indexing and Retrieval , 2005, CIVR.

[17]  Monique Thonnat,et al.  A knowledge-based approach to integration of image processing procedures , 1993 .

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

[19]  Thomas R. Gruber,et al.  Toward principles for the design of ontologies used for knowledge sharing? , 1995, Int. J. Hum. Comput. Stud..

[20]  Céline Hudelot.  Towards a Cognitive Vision Platform for Semantic Image Interpretation; Application to the Recognition of Biological Organisms , 2005 .

[21]  David Sinclair,et al.  Language-based querying of image collections on the basis of an extensible ontology , 2004, Image Vis. Comput..

[22]  Stevan Harnad.  The Symbol Grounding Problem , 1999, ArXiv.

[23]  David A. Bell,et al.  Integrating visual ontologies and wavelets for image content retrieval , 1998, Proceedings Ninth International Workshop on Database and Expert Systems Applications (Cat. No.98EX130).