Oriented edge forests for boundary detection
Sam Hallman, Charless C. Fowlkes · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2015
We present a simple, efficient model for learning boundary detection based on a random forest classifier. Our approach combines (1) efficient clustering of training examples based on a simple partitioning of the space of local edge orientations and (2) scale-dependent calibration of individual tree output probabilities prior to multiscale combination. The resulting model outperforms published results on the challenging BSDS500 boundary detection benchmark. Further, on large datasets our model requires substantially less memory for training and speeds up training time by a factor of 10 over the structured forest model.
Cited by 177 works. doi:10.1109/cvpr.2015.7298782 Open-access PDF
Authors
References
- Classification and Regression Trees.
- Classification and Regression Trees.
- A Computational Approach to Edge Detection
- Classification and regression trees
- The design and use of steerable filters
- Contour Detection and Hierarchical Image Segmentation
- Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods
- Multiscale Combinatorial Grouping
- Learning to detect natural image boundaries using local brightness, color, and texture cues
- Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons