{"type":"ScholarlyArticle","title":"VISUAL INFORMATION PROCESSING: The structure and creation of visual repr~entations","authors":[],"abstract":"For human v1s1on to be explained by a computational theory, the first question is plain: \\\\'hat are the problems the brain solves when we see? It is argued that vision is the construction of efficient symbolic descriptions from images of the world. An important aspect of vision is therefore the choice of representations for the different kinds of information in a visual scene. An overall framework is suggested for extracting shape information from images, in which the analysis proceeds through three representations; (1) the primal sketch, which mates explicit the intensity changes and local two-dimensional geometry of an image, (2) the 2 1/2-D sketch, which is a viewer-centred representation of the depth, orientation and discontinuities of the visible surfaces, and (3) the 3-D model representation, which allo11•s an object-centred description of the threedimensional structure and organization of a viewed shape. The critical act in formulating computational theories for processes capable of constructing these representations is the discovery of valid constraints on the way the world behave:;, that provide sufficient additional information to allow recovery of the desired character! stic. Finally, once a computational theory for a process has been formulated, algorithms for implementing it may be designed, and their performance compared with that of the human visual processor.","doi":null,"url":"https://ijcai.org/proceedings/1979/234","pdf":"https://ijcai.org/proceedings/1979/0234.pdf","markdown":"https://ijcai.org/proceedings/1979/234.md","bibtex":"https://ijcai.org/proceedings/1979/bibtex/234","volume":{"slug":"1979","title":"Proceedings of the Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1979","url":"https://ijcai.org/proceedings/1979/","year":1979,"location":"Tokyo, Japan","dates":"August 20-23, 1979","editors":"Bruce G. Buchanan","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":234,"pages":{"first":null,"last":null},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}