{"type":"ScholarlyArticle","title":"Scale-Space Filtering","authors":[{"name":"Andrew P. Witkin","slug":"andrew-p-witkin","given":"Andrew P.","family":"Witkin","affiliation":""}],"abstract":"The extrema in a signal and its first few derivatives provide a useful general-purpose qualitativedescription for many kinds of signals. A fundamental problem in computing such descriptions is scale: a derivative must be taken over some neighborhood, but there is seldom a principled basis for choosing its size. Scale-space filtering is a meth od that describes signals qualitatively, managing the ambiguity of scale in an organized and natural way. The signal is first expanded by convolution with gaussian masks over a continuum of sizes. This \"scale-space\" image is then collapsed, using its qualitative structure, into a tree providing a concise but complete qualitative description covering all scales of observation. The description is further refined by applying a stability criterion, to identify events that persist of large changes in scale.","doi":null,"url":"https://ijcai.org/proceedings/1983/235","pdf":"https://ijcai.org/proceedings/1983/0235.pdf","markdown":"https://ijcai.org/proceedings/1983/235.md","bibtex":"https://ijcai.org/proceedings/1983/bibtex/235","volume":{"slug":"1983","title":"Proceedings of the Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1983","url":"https://ijcai.org/proceedings/1983/","year":1983,"location":"Karlsruhe, West Germany","dates":"","editors":"Alan Bundy","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Vision","track":"Vision","number":235,"pages":{"first":1019,"last":1021},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}