Geometric Algebra Neuron for SAR Automation Target Recognition
Biometric Pattern Recognition aim at finding the best coverage of per kind of sample’s distribution in the feature space. This paper employed geometric algebra to determine local continuum (connected) direction and connected path of same kind of target of SAR images of the complex geometrical body in high dimensional space. We researched the property of the GA Neuron of the coverage body in high dimensional space and studied a kind of SAR ATR(SAR automatic target recognition) technique which works with small data amount and result to high recognizing rate. Finally, we verified our algorithm with MSTAR (Moving and Stationary Target Acquisition and Recognition)  data set.
W. M. Cao et al., "Geometric Algebra Neuron for SAR Automation Target Recognition", Advanced Materials Research, Vol. 187, pp. 319-325, 2011