Research of pattern recognition based on the local structure topological relationship modeling
Yinxue Qin, Lin Ma, Haifeng Li, Qiuhua Wei · 2012
The article is mainly to study a pattern recognition method which is based on the local structure feature and spatial topological relationship modeling. From the perspective of human cognition and bio-mimetic pattern recognition principle, analyzing things' local structural feature and the overall topological relationship we can achieve things "cognitive" by using ANN(Artificial Neural Network) and HMM(Hidden Markov Model), so in this paper we propose a common pattern recognition method. This method with a strong anti-interference and resistance to deformation reflects the characteristics of things which is similar to human cognition. The experimental results show that this method can apply to the general pattern recognition.