Edge detector evaluation using empirical ROC curves

By Kevin W. Bowyer, Christine Kranenburg, Sean Dougherty. 1999

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, background): “Unfortunately, many visually salient edges do not correspond to color gradients, such as texture edges [34] and illusory contours [39].”
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection (2014, background): “A detailed survey of edge detection methods can be found in [4, 30].”
Edge and line oriented contour detection: State of the art (2011, background): “Therefore, more recently GT based quantitative performance evaluation has been carried out for natural images as well [2,281].”
Submitted to Ieee Transactions on Pattern Analysis and Machine Intelligence Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues (unknown): “A similar approach was taken by Bowyer et al. [30] for boundary detector evaluation with Receiver operating characteristic (ROC) curves.”
Image Parsing: Unifying Segmentation, Detection, and Recognition (2003, unknown): “These cues are based on edge detectors [9],[8],[26].”
Fast Edge Detection Using Structured Forests (2016, background): “Alternatively, a common approach for singlevariate regression (Y = R) is to minimize the variance of labels at the leaves [4] .”
Learning affinity functions for image segmentation: combining patch-based and gradient-based approaches (2003, background): “The next section will cover the choice of the intervening contour function, as well as the best way to combine the contour information from the brightness, color, and texture channels.”
Moving Object Detection in Spatial Domain using Background Removal Techniques - State-of-Art (2008, methodology): “When comparing background removal algorithms [149] or evaluating computer vision systems [176, 177], ROC analysis is often employed when there are known background and foreground (target) distributions, i.”
Structured Forests for Fast Edge Detection (2013, background): “An evaluation of various low-level edge detectors can be found in [3] and an overview in [38].”
Deep Nets: What have They Ever Done for Vision? (2018, background): “(Bowyer et al., 1999), corresponded to images of the English countryside and indoor images in Florida.”
Evaluation of Interest Point Detectors (2000, methodology): “Existing evaluation methods use ground-truth verification (Bowyer et al., 1999), visual inspection (Heath et al., 1997; López et al., 1999), localization accuracy (Baker and Nayar, 1999; Brand and Mohr, 1994; Coelho et al., 1991; Heyden and Rohr, 1996), theoretical analysis (Demigny and Kamlé,…”
Contour detection based on nonclassical receptive field inhibition (2003, background): “Consequently, much research has been done in this area and a considerable body of literature has been accumulated [1]–[12].”
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–”
Complex Wavelet Structural Similarity: A New Image Similarity Index (2009, methodology): “[14].”