A Computational Approach to Edge Detection

By John F. Canny. 1986

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Soft-NMS — Improving Object Detection with One Line of Code (2017, background): “In edge detection, NMS performs dge thinning t remove spur us responses [22, 1, 29].”
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (2019, methodology): “Canny edge detector, an early scheme for constructing edge maps, for example, is roughly 30 years old [6].”
Holistically-Nested Edge Detection (2015, methodology): “In the third row: (g), (h), and (i), respectively, show edge responses from the Canny detector [4] at the scales σ = 2 .”
Fast Edge Detection Using Structured Forests (2014, background): “The detection of edges is a critical preprocessing step for a variety of tasks, including object recognition [47], [17], segmentation [33], [1], and active contours [26].”
Learning visual groups from co-occurrences in space and time (2015, background): “Visual grouping is also a central problem in computer vision, showing up in the tasks of edge/contour detection Canny (1986); Arbelaez et al. (2011); Isola et al. (2014) , (semantic) segmentation Shi & Malik (2000); Malisiewicz & Efros (2007), and object proposals Alexe et al. (2012); Zitnick &…”
Determinantal Point Processes for Machine Learning (2012, background): “The second baseline is a simple non-maximum suppression model [22], which incorporates a heuristic for encouraging diversity.”
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection (2014, methodology): “To extract a set of candidate contours with high recall we apply the Canny edge detector [5] to the input image.”
Unsupervised Learning of Edges (2015, methodology): “Edge Detection: Early edge detectors were manually designed to use image gradients [14, 8, 15] and later texture gradients [2].”
Pixel-wise Deep Learning for Contour Detection (2015, methodology): “Prior to evaluation, we apply a standard non-maximal suppression technique to edge maps to obtain thinned edges (Canny, 1986).”
An Analysis of Scale Invariance in Object Detection - SNIP (2017, background): “Scale space theory [35, 26] advocates learning representations that are invariant to scale and the theory has been applied to many problems in the history of computer vision [4, 30, 28, 21, 14, 5, 23].”
Oriented edge forests for boundary detection (2014, background): “tant ﬁrst step for segmentation and detection of objects in a scene and boundaries provide useful information about the shape and identity of those objects. Early work such as the Canny edge detector [6] focused on detecting brightness edges, estimating their orientation [12] and analyzing the theor”
Text-based CAPTCHA strengths and weaknesses (2011, methodology): “However, it is susceptible to line-finding algorithms, such as the Canny edge detection [6] and the Hough Transform [13], because the lines cross the entire captcha.”
Counting People With Low-Level Features and Bayesian Regression (2012, methodology): “A Canny edge detector [43] is applied to the image, the output is masked to form the internal edge image (see Fig.”
Medical Image Registration (2001, methodology): “5 The Canny Edge Detector In 1983, John Canny introduced the Canny edge detection scheme [1] and it has since then been the standard edge detection scheme used around the world [33].”
A review of speckle filtering in the context of estimation theory (2002, background): “, see [1], [2], [4], [29], [33], and [47]) might be used to match the best local nonstationarity.”