摘要
本文从语义、句法模式识别观点,提出一种基于模型指导的有限状态属性自动机,进行特征抽取,对每一种典型的畸变模型设计一个有限状态属性文法及其相应的属性自动机,采用自下而上和自上而下相结合的控制策略,并在低层次引入知识指导,减少了工作量和不确定性。基于上述方法实现的非限制性手写数字识别系统,经过对1100个非限制性手写数字样本的测试,平均识别率达95.2％,拒识率为4.6％,误识率为0.2％。
In this paper, a model-based finite state attribute automaton is proposed from syntatic and semantic recognition point view for the extraction of features. For each typical deformed model, a new finite state attribute grammar and its corresponding automaton is designed. This method combines Top-Down and Bottom-Up control strategy, introduces knowledge in low levels, this cuts down the amount of operations and reduces the uncertainty. An unconstrained handwritten numerals recognition system is realized based on this approach. By testing a set of 1, 100 samples, the average recognition ratte is 95.2%, rejection rate is 4.6%, substitution rate is 0.2%.
出处
《自动化学报》
EI
CSCD
北大核心
1993年第5期578-586,共9页
Acta Automatica Sinica
基金
国家自然科学基金
863计划的资助
关键词
模式识别
手写体
数字识别
Pattern recognition
primitive
attributed grammar
automata.
