Edge Detection

By Ellen C. Hildreth. 1985

How researchers see this paper

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

Citations in the corpus

PASCAL Boundaries: A Class-Agnostic Semantic Boundary Dataset (2015, methodology): “…active research and potential solutions include local ﬁltering-based approaches like the Canny edge detector [5] and the zero-crossing algorithm [26], to pixel-level classiﬁcation methods that use features obtained by careful manual design like gPb [1], to patch-based clustering algorithms such…”
Learning to predict crisp boundaries (2018, background): “In early years, the objective is defined as to find sudden changes of discontinuities in intensity images [3].”
A Computational Approach to Edge Detection (1986, unknown): “The form of nonlinear second derivative operator in (47) has also been used by Torre and Poggio [28] and by Haralick [10].”
Robust Object Recognition with Cortex-Like Mechanisms (2007, methodology): “They are also very similar to DoG filters used since the 1960s to model receptive fields in the retina and primary visual cortex and to perform edge detection in computer vision (see [56], [57]).”
Markov Random Field Modeling in Image Analysis (2001, background): “1982; Cross and Jain 1983), edge detection (Torre and Poggio 1986; Tan et al. 1992), image segmentation (Silverman and Cooper 1988; Li 1990a), perceptual grouping (Lowe 1985; Mohan and Nevatia 1989; Herault and Horaud 1993), interpretation of line drawings (Leclerc and Fischler 1992), object matchin”
Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion (2011, background): “Torre and Poggio [104] also note that filtering of a sampled image prior to differentiation is necessary to regularize the problem of computing derivatives in an intensity image.”
Edge Detection Techniques-An Overview (1998, unknown): “With regards to the in(cid:13)uence of form attributes and smoothness, it is pointed out that directional operators are suitable for the extraction of straight edges [7, 114].”
Pixel Difference Networks for Efficient Edge Detection (2021, background): “The main goal of edge detection is identifying sharp image brightness changes such as discontinuities in intensity, color, or texture [53].”
End-to-End Instance Edge Detection (2022, methodology): “Early pioneering methods include the Sobel filter [33], zerocrossing [46,57], and Canny edge detector [5].”
FABC: Retinal Vessel Segmentation Using AdaBoost (2010, background): “D Gaussians (emphasizing regions) and its derivatives of first order (emphasizing Canny-like edges [33]) and second order (emphasizing zero-crossings [34] Gaussian function with variance t, I is an image, (x, y) is a pixel location, and * represents the convolution operation.”