标题：Metal label pressed protuberant characters recognition based on hidden Markov model
作者机构：[Chen, Wei ] College of Automation and Electronics Engineering, Qingdao University of Science and Technology, Qingdao, China;[Chen, Wei ] School of Me 更多
会议名称：2011 International Conference on Sport Material, Modelling and Simulation, ICSMMS 2011
会议日期：27 January 2011 through 28 January 2011
来源：Advanced Materials Research
关键词：Characters recognition; Hidden Markov models; Neural Network; Pressed protuberant characters; Shape from shading; Shape index
摘要：A recognition method of pressed protuberant characters based on Hidden Markov models and Neural Network is applied, which the surface curvature properties and the relation of metal label characters are analyzed in detail. The shape index of the characters is extracted. A neural network is used to estimate probabilities for the characters depended on the surface curvature properties, then deriving the best word choice from a sequence of state transition. It is shown in test that the proposed method can be used to recognize the pressed protuberant on metal label. © (2011) Trans Tech Publications.