Feature space trajectory neural net classifier
Leonard Neiberg, David P. Casasent · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1995
A new classifier neural network is described for distortion-invariant multi-class pattern recognition. The input analog neurons are a feature space. All distorted aspect views of one object are described by a trajectory in feature space. Classification of test data involves calculation of the closest feature space trajectory. Pose estimation is achieved by determining the closest line segment on the closest trajectory. Rejection of false class clutter is demonstrated. Comparisons are made to other neural network classifiers, including a radial basis function and a new standard backpropagation neural net. The shapes of the different decision surfaces produced by our feature space trajectory classifier are analyzed.