Fast Edge Detection Using Structured Forests

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.

update corresponding to acceptance to PAMI

References in corpus (1)

• Generalized Boundaries from Multiple Image Interpretations

Cited by in corpus (8)

• Holistically-Nested Edge Detection
• Reading Text in the Wild with Convolutional Neural Networks
• SegFix: Model-Agnostic Boundary Refinement for Segmentation
• Oriented Edge Forests for Boundary Detection
• Improved Image Boundaries for Better Video Segmentation
• Weakly Supervised Object Boundaries
• Contour Detection Using Cost-Sensitive Convolutional Neural Networks
• Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network