Hopfield network with constraint parameter adaptation for overlapped shaperecognition

In this paper, we propose an energy formulation for homomorphic graph match ing by the Hopfield network and a Lyapunov indirect method-based learning a pproach to adaptively learn the constraint parameter in the energy function , The adaptation scheme eliminates the need to specify the constraint param eter empirically and generates valid and better quality mappings than the a nalog Hopfield network with a fixed constraint parameter, The proposed Hopf ield network with constraint parameter adaptation is applied to match silho uette images of keys and results are presented.