A translation/rotation/scaling/occlusion invariant neural network for 2D/3D object classification
Jenq–Neng Hwang, Hongwei Li · 1992
Classifying objects that are distorted by similarity transforms and detection/occlusion noise is a difficult pattern recognition task. A novel and robust neural network solution based on detected surface boundary points is presented. The method operates in two stages. The object is first parametrically represented by a surface reconstruction neural network (SRNN) trained by the boundary points sampled from the exemplar object. When later presented with a distorted object, this parametric representation reduces the effects caused by detection/occlusion and also allows the mismatch information backpropagated through the SRNN to iteratively determine the best similarity transform of the distorted object. The distance measure can then be computed in the reconstructed representation domain between the exemplar object and the aligned distorted object.>