On the accuracy of the Sobel edge detector

How researchers see this paper

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

EDTER: Edge Detection with Transformer (2022, methodology): “Early edge detectors [6, 28, 63], such as Sobel [28] and Canny [6], focus on analysing the image gradients to extract the edges.”
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks (2016, background): “rks are publicly available at www.vision. ee.ethz.ch/˘cvlsegmentation/. 2 RELATED WORK Contour Detection: Early approaches to contour detection relied on local gradient measurements in an image [20], [21], [22]. These simple edge detectors operate by applying local derivative ﬁlters on grayscale ima”
Learning to predict crisp boundaries (2018, methodology): “For example, the Sobel detector [18] slides a 3×3 filter on a gray image to compute the image gradient for the response to the edge pixel.”
Bi-Directional Cascade Network for Perceptual Edge Detection (2019, background): “Traditional edge operators [22, 4, 45, 34] detect edges by finding sudden changes in intensity, color, texture, etc.”
RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth (2021, background): “Early edge detectors [5, 19, 42] obtain edges based directly on the analysis of image gradients.”
End-to-End Instance Edge Detection (2022, methodology): “Early pioneering methods include the Sobel filter [33], zerocrossing [46,57], and Canny edge detector [5].”
Deep Structural Contour Detection (2020, background): “Early works can be traced back forty years ago [18].”