This document proposes two tensor voting (TV) based binary classification algorithms and evaluates them experimentally on real and synthetic data.
The first algorithm (TVBC1) finds potential decision boundary points by matching closest training points from different classes. It then models the decision boundary using local planes estimated with TV. Test points are classified based on these local plane equations.
The second algorithm (TVBC2) computes a class similarity measure for each test point that combines distance and orientation alignment with training points. The test point is assigned to the class with the best similarity measure.
Experiments on synthetic and real data validate the approaches and compare their accuracy and time performance to standard classifiers like k-nearest neighbors and decision trees.