arXiv (Cornell University) · 2013 · 15 citations · 25 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningFeature DescriptionFeature DetectionPattern RecognitionShape AnalysisShape RepresentationTrajectory AnalysisAutomated Machine LearningCurve RepresentationInvariant Feature RepresentationInvariantsIterated IntegralsShape Feature ExtractionShape FeaturesShape Recognition
We introduce a novel class of rotation invariants of two dimensional curves based on iterated integrals. The invariants we present are in some sense complete and we describe an algorithm to calculate them, giving explicit computations up to order six. We present an application to online (stroke-trajectory based) character recognition. This seems to be the first time in the literature that the use of iterated integrals of a curve is proposed for (invariant) feature extraction in machine learning applications.
25
Visual pattern recognition by moment invariants
Ming-Kuei Hu · IRE Transactions on Information Theory · 1962 · 7.5K citations
Fourier Descriptors for Plane Closed Curves
C. T. Zahn, Ralph Roskies · IEEE Transactions on Computers · 1972 · 1.9K citations
Differential equations driven by rough signals
Terry Lyons · Revista Matemática Iberoamericana · 1998 · 1.1K citations · Full text