Boundary Learning by Optimization with Topological Constraints
- 1 June 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2488-2495
- https://doi.org/10.1109/cvpr.2010.5539950
Abstract
Recent studies have shown that machine learning can improve the accuracy of detecting object boundaries in images. In the standard approach, a boundary detector is trained by minimizing its pixel-level disagreement with human boundary tracings. This naive metric is problematic because it is overly sensitive to boundary locations. This problem is solved by metrics provided with the Berkeley Segmentation Dataset, but these can be insensitive to topological differences, such as gaps in boundaries. Furthermore, the Berkeley metrics have not been useful as cost functions for supervised learning. Using concepts from digital topology, we propose a new metric called the warping error that tolerates disagreements over boundary location, penalizes topological disagreements, and can be used directly as a cost function for learning boundary detection, in a method that we call Boundary Learning by Optimization with Topological Constraints (BLOTC). We trained boundary detectors on electron microscopic images of neurons, using both BLOTC and standard training. BLOTC produced substantially better performance on a 1.2 million pixel test set, as measured by both the warping error and the Rand index evaluated on segmentations generated from the boundary labelings. We also find our approach yields significantly better segmentation performance than either gPb-OWT-UCM or multiscale normalized cut, as well as Boosted Edge Learning trained directly on our data.Keywords
This publication has 21 references indexed in Scilit:
- Supervised Learning of Image Restoration with Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Automating the Collection of Ultrathin Serial Sections for Large Volume TEM ReconstructionsMicroscopy and Microanalysis, 2006
- Supervised Learning of Edges and Object BoundariesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Serial Block-Face Scanning Electron Microscopy to Reconstruct Three-Dimensional Tissue NanostructurePLoS Biology, 2004
- Learning affinity functions for image segmentation: combining patch-based and gradient-based approachesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Distance-Ordered Homotopic Thinning: A Skeletonization Algorithm for 3D Digital ImagesComputer Vision and Image Understanding, 1998
- Topology-Preserving Deformations of Two-Valued Digital PicturesGraphical Models and Image Processing, 1998
- A new characterization of three-dimensional simple pointsPattern Recognition Letters, 1994
- Digital topology: Introduction and surveyComputer Vision, Graphics, and Image Processing, 1989
- Objective Criteria for the Evaluation of Clustering MethodsJournal of the American Statistical Association, 1971