Raisonnement abductif en logique de description exploitant les domaines concrets spatiaux pour l'interprétation d'images

RÉSUMÉ. L’interprétation d’images a pour objectif non seulement de détecter et reconnaître des objets dans une scène mais aussi de fournir une description sémantique tenant compte des informations contextuelles dans toute la scène. Le problème de l’interprétation d’images peut être formalisé comme un problème de raisonnement abductif, c’est-à-dire comme la recherche de la meilleure explication en utilisant une base de connaissances. Dans ce travail, nous présentons une nouvelle approche utilisant une méthode par tableau pour la génération et la sélection d’explications possibles d’une image donnée lorsque les connaissances, exprimées dans une logique de description, comportent des concepts décrivant les objets mais aussi les relations spatiales entre ces objets. La meilleure explication est sélectionnée en exploitant les domaines concrets pour évaluer le degré de satisfaction des relations spatiales entre les objets.

[1]  Isabelle Bloch,et al.  Explanatory Reasoning for Image Understanding Using Formal Concept Analysis and Description Logics , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[2]  Georg Gottlob,et al.  The Complexity of Logic-Based Abduction , 1993, STACS.

[3]  Isabelle Bloch,et al.  Fuzzy spatial relationships for image processing and interpretation: a review , 2005, Image Vis. Comput..

[4]  Jerry R. Hobbs.  Abduction in Natural Language Understanding , 2008 .

[5]  Raymond Reiter,et al.  A Theory of Diagnosis from First Principles , 1986, Artif. Intell..

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

[7]  Isabelle Bloch,et al.  Sequential model-based segmentation and recognition of image structures driven by visual features and spatial relations , 2012, Comput. Vis. Image Underst..

[8]  Isabelle Bloch,et al.  From Generic Knowledge to Specific Reasoning for Medical Image Interpretation Using Graph based Representations , 2007, IJCAI.

[9]  Christopher Town,et al.  Ontological inference for image and video analysis , 2006, Machine Vision and Applications.

[10]  Franz Baader.  Least Common Subsumers and Most Specific Concepts in a Description Logic with Existential Restrictions and Terminological Cycles , 2003, IJCAI.

[11]  Franz Baader,et al.  A Scheme for Integrating Concrete Domains into Concept Languages , 1991, IJCAI.

[12]  Mubarak Shah,et al.  UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild , 2012, ArXiv.

[13]  C. Peirce,et al.  Collected Papers of Charles Sanders Peirce , 1936, Nature.

[14]  Isabelle Bloch,et al.  Fuzzy spatial relation ontology for image interpretation , 2008, Fuzzy Sets Syst..

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[18]  Alessandro Saffiotti,et al.  Anchoring Symbols to Sensor Data: Preliminary Report , 2000, AAAI/IAAI.

[19]  Ulrike Sattler,et al.  A Case for Abductive Reasoning over Ontologies , 2006, OWLED.

[20]  Isabelle Bloch,et al.  A constraint propagation approach to structural model based image segmentation and recognition , 2013, Inf. Sci..

[21]  Ian Horrocks,et al.  A Description Logic with Transitive and Inverse Roles and Role Hierarchies , 1999, J. Log. Comput..

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

[23]  Antonio Torralba,et al.  LabelMe: A Database and Web-Based Tool for Image Annotation , 2008, International Journal of Computer Vision.

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

[25]  Stefan Schlobach,et al.  ABox Abduction in the Description Logic ALC , 2011, J. Autom. Reason..

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

[27]  Meghyn Bienvenu,et al.  Complexity of Abduction in the EL Family of Lightweight Description Logics , 2008, KR.

[28]  Murray Shanahan,et al.  Perception as Abduction: Turning Sensor Data Into Meaningful Representation , 2005, Cogn. Sci..

[29]  H. Carter.  Fuzzy Sets and Systems — Theory and Applications , 1982 .

[30]  C. Hartshorne,et al.  Collected Papers of Charles Sanders Peirce , 1935, Nature.

[31]  Francesco M. Donini,et al.  A Uniform Tableaux-Based Approach to Concept Abduction and Contraction in ALN , 2004, Description Logics.

[32]  Marie-Laure Mugnier,et al.  Graph-based Knowledge Representation - Computational Foundations of Conceptual Graphs , 2008, Advanced Information and Knowledge Processing.

[33]  José L. V. Mejino,et al.  A reference ontology for biomedical informatics: the Foundational Model of Anatomy , 2003, J. Biomed. Informatics.