Fast Edge Detection Using Structured Forests
Top Cited Papers
- 4 December 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (8), 1558-1570
- https://doi.org/10.1109/tpami.2014.2377715
Abstract
Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Patches of edges exhibit well-known forms of local structure, such as straight lines or T-junctions. In this paper we take advantage of the structure present in local image patches to learn both an accurate and computationally efficient edge detector. We formulate the problem of predicting local edge masks in a structured learning framework applied to random decision forests. Our novel approach to learning decision trees robustly maps the structured labels to a discrete space on which standard information gain measures may be evaluated. The result is an approach that obtains realtime performance that is orders of magnitude faster than many competing state-of-the-art approaches, while also achieving state-of-the-art edge detection results on the BSDS500 Segmentation dataset and NYU Depth dataset. Finally, we show the potential of our approach as a general purpose edge detector by showing our learned edge models generalize well across datasets.Keywords
Other Versions
This publication has 38 references indexed in Scilit:
- Multiscale Combinatorial GroupingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Generalized Boundaries from Multiple Image InterpretationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Sketch Tokens: A Learned Mid-level Representation for Contour and Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Structured class-labels in random forests for semantic image labellingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Boundary Detection Using F-Measure-, Filter- and Feature- (F3) BoostLecture Notes in Computer Science, 2010
- Structured Learning and Prediction in Computer VisionFoundations and Trends® in Computer Graphics and Vision, 2010
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statisticsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Contour and Texture Analysis for Image SegmentationInternational Journal of Computer Vision, 2001
- Scale-space and edge detection using anisotropic diffusionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990