Gaby J. Salem

A neural network approach to the labeling of line drawings

A solution to the labeling of the drawings using a neural network approach is presented. Line-labeling constraints are designed into a modified Hopfield networks. The design of the energy function and the updating equation is described. The energy function includes higher order terms than in the usual quadratic Hopfield model to accommodate the higher-order interactions required by the labeling constraints. The physical model is modified accordingly. An additional layer of neurons is used to synthesize a realizable circuit. The resulting network combines the standard Hopfield-network neurons with neurons performing two- and three-way Boolean AND operations. Simulation of network behavior for various trihedral scenes produced successful results. >

Interpreting line drawings with higher order neural networks

A neural network solution to line labeling is presented. Line labeling constraints in trihedral scenes are designed into a Hopfield-type network. The labeling constraints require a higher-order of interaction than that of Hopfield and Tanks (1985) quadratic energy model. The analog model is modified to include an additional layer of neurons. A brief introduction to the line labeling problem is provided. The design of the energy function and the updating equation is described. Experimental results are analyzed.<<ETX>>