Level Learning Set: A Novel Classifier Based on Active Contour Models

Abstract

This paper presents a novel machine learning algorithm for pattern classification based on image segmentation and optimisation techniques employed in active contour models and level set methods. The proposed classifier, named level learning set (LLS), has the ability to classify general datasets including sparse and non sparse data. It moves developments in vision segmentation into general machine learning by utilising and extending level set-based active contour models from the field of computer vision to construct decision boundaries in any feature space. This model has advantages over traditional classifiers in its ability to directly construct complex decision boundaries, and in better knowledge representation. Various experimental results including comparisons to existing machine learning algorithms are presented, and the advantages of the proposed approach are discussed.KeywordsFeature SpaceActive ContourDecision BoundaryActive Contour ModelUnanimity RuleThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.