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

Author

Kim, Jung H. ; Yoon, Sung H. ; Kim, Yong H. ; Park, Eui H. ; Ntuen, C. ; Sohn, Kwang H. ; Alexander, Winser E.

Author_Institution

North Carolina A&T State Univ., Greensboro, NC, USA

Volume

6

fYear

1992

fDate

10-13 May 1992

Firstpage

2888

Abstract

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

Keywords

Hopfield neural nets; image recognition; continuous Hopfield network; discrete Hopfield network; global minimum; hybrid Hopfield network; matching algorithm; neuron outputs; object recognition; reliability; speed; two-dimensional occlusion problems; Computational modeling; Differential equations; Hopfield neural networks; Neural networks; Neurons; Object recognition; Robotics and automation; Shape; Stochastic processes; Traveling salesman problems;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on

Conference_Location

San Diego, CA

Print_ISBN

0-7803-0593-0

Type

conf

DOI

10.1109/ISCAS.1992.230647

Filename

230647