An efficient matching algorithm by a hybrid Hopfield network for object recognition

Hopfield proposed two types of neural networks, the discrete Hopfield network (DHN) and the continuous Hopfield network (CHN). A new method for two-dimensional object recognition using a Hopfield neural network is proposed. A hybrid Hopfield network (HHN), which combines the merit of both the continuous Hopfield network and the discrete Hopfield network, is proposed and some of the advantages such as reliability and speed are discussed. Stable states of neurons are analyzed and predicted based upon the theory of the CHN after convergence in the DHN. The experiments showed that once solutions close to a global minimum were obtained in the DHN, the HHN can find the desired output by adjusting the states of neuron outputs. HHN is a robust approach to solve two-dimensional occlusion problems