Sketch learning by analogy
Autor(en): | Krumnack, U. Schwering, A. Kühnberger, K.-U. Gust, H. Abdel-Fattah, A. Besold, T. Schmidt, M. Schneider, S. |
Herausgeber: | Kutz, O. Borgo, S. Bhatt, M. Santos, P. |
Stichwörter: | Analogy; Cognitive science; Learning; Reasoning techniques; Shape; Sketch; Spatial arrangements; Three-level | Erscheinungsdatum: | 2013 | Herausgeber: | CEUR-WS | Enthalten in: | CEUR Workshop Proceedings | Band: | 1007 | Startseite: | 49 | Seitenende: | 58 | Zusammenfassung: | Sketches are shapes that represent objects, scenes, or ideas by depicting relevant parts and their spatial arrangements. While humans are quite efficient in understanding and using sketch drawings, those are largely inaccessible to computers. We argue that this is due to a specific shape based representation by humans and hence the use of cognitively inspired representation and reasoning techniques could lead to more proficient sketch processing. We also propose a three-level architecture for sketch learning and recognition that builds on concepts from cognitive science, especially from analogy research, to map and generalize sketches. Copyright © 2013 for the individual papers by the papers' authors. |
Beschreibung: | Conference of 2nd Interdisciplinary Workshop the Shape of Things ; Conference Date: 3 April 2013 Through 4 April 2013; Conference Code:110972 |
ISSN: | 16130073 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84923683269&partnerID=40&md5=78281463ef3f625432a16c85de5fbdf8 |
Zur Langanzeige