Sketch Learning by Analogy
نویسندگان
چکیده
Sketches are shapes that represent objects, scenes, or ideas by depicting relevant parts and their spatial arrangements. While humans are quite e cient 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.
منابع مشابه
Deconstructing analogy
Analogy has been shown to be important in many key cognitive abilities, including learning, problem solving, creativity and language change. For cognitive models of analogy, the fundamental computational question is how its inherent complexity (its NP-hardness) is solved by the human cognitive system. Indeed, different models of analogical processing can be categorized by the simplification str...
متن کاملEvaluation of the Sketch Engine Thesaurus on Analogy Queries
Recent research on vector representation of words in texts bring new methods of evaluating distributional thesauri. One of such methods is the task of analogy queries. We evaluated the Sketch Engine thesaurus on a subset of analogy queries using several similarity options. We show that Jaccard similarity is better than the cosine one for bigger corpora, it even substantially outperforms the wor...
متن کاملIncremental Learning of Perceptual Categories for Open-Domain Sketch Recognition
Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for opendomain recognition. Our system builds generalizations for categories of objects based upon previous sketches of those objects and uses those generalizations to classify new sketches. We represent sketches qualitatively because we believe quali...
متن کاملSketch Worksheets: A Sketch-Based Educational Software System
Intelligent tutoring systems and learning environments can provide important benefits for education, but few have been developed for heavily spatial domains. One bottleneck has been the lack of rich models of visual and conceptual processing in sketch understanding, so that what students draw can be interpreted in a human-like way. This paper describes Sketch Worksheets, a form of sketch-based ...
متن کاملEfficient Learning of Qualitative Descriptions for Sketch Recognition
We are trying to solve the problem of learning to recognize objects in an open-domain sketching environment. Our system builds generalizations of objects based upon previous sketches of those objects and uses those generalizations to classify new sketches. We represent sketches qualitatively because we believe qualitative information provides a level of description that abstracts away details t...
متن کامل