ClassySeg: A Machine Learning Approach to AutomaticStroke Segmentation

Simple item page
dc.contributor.authorHerold, J.en_US
dc.contributor.authorStahovich, T. F.en_US
dc.contributor.editorTracy Hammond and Andy Nealenen_US
dc.date.accessioned2013-10-31T10:24:23Z
dc.date.available2013-10-31T10:24:23Z
dc.date.issued2011en_US
dc.description.abstractWe present ClassySeg, a technique for segmenting hand-drawn pen strokes into lines and arcs. ClassySeg employs machine learning techniques to infer the segmentation intended by the drawer. The technique begins by identifying a set of candidate segment points, consisting of all curvature maxima. Features are computed for each candidate point based on speed, curvature, and other geometric properties. These features are adapted from numerous prior segmentation approaches, effectively combining their strengths. These features are used to train a statistical classifier to identify which candidate points are true segment points. A beam search is used to approximate the optimal subset of features to use as input to the classifier. ClassySeg is more accurate than previous techniques foruser-independent training conditions, and is as good as the current state-of-the-art algorithm for user-optimized conditions. More importantly, ClassySeg represents a movement away from prior heuristic-based approaches towards a more general and extensible approach.en_US
dc.description.seriesinformationEurographics Workshop on Sketch-Based Interfaces and Modelingen_US
dc.identifier.isbn978-1-4503-0906-6en_US
dc.identifier.issn1812-3503en_US
dc.identifier.urihttps://doi.org/10.2312/SBM/SBM11/109-116en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectCategories and Subject Descriptors (according to ACM CCS): I.4.6 [Computer Graphics]: Image Processing andComputer Vision Segmentation - Edge and feature detectionen_US
dc.titleClassySeg: A Machine Learning Approach to AutomaticStroke Segmentationen_US
Files
Collections
SBM11: Sketch Based Interfaces and Modeling 2011