An initial assessment of discriminant surface complexity for power law features
Jeffrey L. Solka, Carey E. Priebe, George W. Rogers · SIMULATION · 1992
The detection of man-made objects in natural terrain is important in both the targeting and terminal homing phase of modern warfare. The presence of man-made objects in gray-scale images has been successfully detected using a new class of density estimation neural networks to analyze power law signatures. The complex nature of the discriminant surface relating these features has been elucidated using these adaptive mixture networks.