On the Quantitative Evaluation of Edge Detection Schemes and their Comparison with Human Performance

By J. Fram, E. Deutsch. 1975

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

Fast Edge Detection Using Structured Forests (2014, methodology): “EDGE detection has remained a fundamental task in computer vision since the early 1970’s [15], [18], [43].”
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].”
Learning to predict crisp boundaries (2018, background): “Early edge detectors focus on computing the image gradients to obtain the edges [18,19,20,21].”
Deep Structural Contour Detection (2020, background): “Early edge detectors such as the Sobel [18] and the Canny [5] detectors focus on computing the image gradients to generate edges [11, 33].”
Structured Forests for Fast Edge Detection (2013, background): “Early work [13, 10, 5, 27, 14] focused on the detection of intensity or color gradients.”
PASCAL Boundaries: A Class-Agnostic Semantic Boundary Dataset (2015, background): “Edge detection has been a fundamental problem in computer vision since the 1970’s [10].”
Moving Object Detection in Spatial Domain using Background Removal Techniques - State-of-Art (2008, methodology): “It can viewed also as the percentage of misclassified edge pixels, eventually weighting the edge pixels in error with a function of their distance to the reference edge, is used by several authors for the evaluation of edge detectors [168, 169].”
Richer Convolutional Features for Edge Detection (2016, background): “Since edge detection was set as one of the most fundamental problems in computer vision [15,18,46], researchers have struggled on it for nearly 50 years, and there have emerged a large number of materials.”
Image segmentation evaluation: A survey of unsupervised methods (2008, methodology): “There are also a variety of discrepancy methods for the evaluation of edge-based image segmentation methods [26–28,67,29–34].”
Deep Crisp Boundaries (2017, background): “Early edge detectors are manually designed to find discontinuities in intensity and color [11, 5, 12].”
A Computational Approach to Edge Detection (1986, unknown): “It was evaluated in Fram and Deutsch [7] and compared very favorably with several other schemes considered in that paper.”