A Pig, an Angel and a Cactus Walk Into a Blender: A Descriptive Approach to Visual Blending

A descriptive approach for automatic generation of visual blends is presented. The implemented system, the Blender, is composed of two components: the Mapper and the Visual Blender. The approach uses structured visual representations along with sets of visual relations which describe how the elements (in which the visual representation can be decomposed) relate among each other. Our system is a hybrid blender, as the blending process starts at the Mapper (conceptual level) and ends at the Visual Blender (visual representation level). The experimental results show that the Blender is able to create analogies from input mental spaces and produce well-composed blends, which follow the rules imposed by its base-analogy and its relations. The resulting blends are visually interesting and some can be considered as unexpected.

[1]  Amílcar Cardoso,et al.  Optimality Principles in Computational Approaches to Conceptual Blending: Do We Need Them (at) All? , 2016, ICCC.

[2]  Lidia Khmylko.  Supervised by : , 1991 .

[3]  Yuri Engelhardt,et al.  The Language of Graphics: A Framework for the Analysis of Syntax and Meaning in Maps, Charts and Diagrams , 2002, ILLC dissertation series.

[4]  J. Goguen.  An introduction to algebraic semiotics, with application to user interface design , 1999 .

[5]  Amílcar Cardoso,et al.  A Model for Creativity in Creature Generation , 2003, GAME-ON.

[6]  Imre Lakatos,et al.  On the Uses of Rigorous Proof. (Book Reviews: Proofs and Refutations. The Logic of Mathematical Discovery) , 1977 .

[7]  C.G. Pereira,et al.  Creativity and Artificial Intelligence: A Conceptual Blending Approach , 2007 .

[8]  Introduction PROTOTYPE THEORY, COGNITIVE LINGUISTICS AND PEDAGOGICAL GRAMMAR , 2022 .

[9]  Tiago Martins,et al.  X-Faces: The eXploit Is Out There , 2016, ICCC.

[10]  Alison Pease,et al.  Using Argumentation to Evaluate Concept Blends in Combinatorial Creativity , 2015, ICCC.

[11]  O. Neurath.  International picture language : the first rules of isotype , 1936 .

[12]  Ping Xiao,et al.  Vismantic: Meaning-making with Images , 2015, ICCC.

[13]  Dan Ventura,et al.  Before A Computer Can Draw, It Must First Learn To See , 2016, ICCC.

[14]  Steve DiPaola,et al.  Deep Convolutional Networks as Models of Generalization and Blending within Visual Creativity , 2016, ICCC.

[15]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[16]  Edward F. McQuarrie,et al.  Beyond Visual Metaphor: A New Typology of Visual Rhetoric in Advertising , 2004 .

[17]  Gilles Fauconnier,et al.  Mental Spaces: Aspects of Meaning Construction in Natural Language , 1985 .

[18]  Kai-Uwe Kühnberger,et al.  Visual Hallucination For Computational Creation , 2016, ICCC.

[19]  Otto Neurath,et al.  International Picture Language , 1936 .

[20]  G. Fauconnier,et al.  The Way We Think , 2002 .

[21]  D. Herrmann.  Proofs And Refutations The Logic Of Mathematical Discovery , 2016 .

[22]  Mark T. Keane,et al.  Setting limits on analogy: Why conceptual combination is not structural alignment. , 2001 .

[23]  Gilles Fauconnier,et al.  Conceptual Integration Networks , 1998, Cogn. Sci..

[24]  Amílcar Cardoso,et al.  The Boat-House Visual Blending Experience , 2002 .