{"type":"ScholarlyArticle","title":"An Optimal Scale for Edge Detection","authors":[{"name":"Davi Geiger","slug":"davi-geiger","given":"Davi","family":"Geiger","affiliation":""},{"name":"Tomaso A. Poggio","slug":"tomaso-a-poggio","given":"Tomaso A.","family":"Poggio","affiliation":""}],"abstract":"Many problems in earl y vision are ill posed 1 . Edge detection is a typical example. This paper applies regularization techniques to the problem of edge detection. We derive an optimal filter for edge detection with a size controlled by .the regularization parameter A and compare it to the Gaussian filter. A formula relating the signal-to-noise ratio to the parameter A is derived from regularization analysis, showing that the scale of the filter is a function of the signal-to-noise ratio. We also discuss the method of Generalized Cross Validation for obtaining the optimal filter scale. Finally, we use our framework to explain two perceptual phenomena: coarsely quantized images becoming recognizable by either blurring or adding noise.","doi":null,"url":"https://ijcai.org/proceedings/1987/150","pdf":"https://ijcai.org/proceedings/1987/0150.pdf","markdown":"https://ijcai.org/proceedings/1987/150.md","bibtex":"https://ijcai.org/proceedings/1987/bibtex/150","volume":{"slug":"1987","title":"Proceedings of the Tenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1987","url":"https://ijcai.org/proceedings/1987/","year":1987,"location":"Milan, Italy","dates":"","editors":"John McDermott","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Perception","track":"Perception","number":150,"pages":{"first":745,"last":747},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}