摘要
为了提高机器识别汉字的容错性和准确性,运用仿生模式识别手写体汉字,并以机器"认知"取代机器对特征样本的"区分",研究了手写体汉字的识别方法。该方法先采用双权值椭圆形神经元对汉字的横、竖、撇、捺4类基本笔段进行覆盖;然后通过分析笔段神经元间的拓扑性质来合成具有容错表征方式的6种汉字笔划类型;接着模仿人类汉字形码输入法,通过统计具有冗余容错形状的笔划神经元类型、数量、位置和相合相交数量,建立了手写体汉字特征知识的数据结构表;最后模仿人学习、记忆及对比判断的能力,先验地建立了标准印刷汉字的样本知识库和容错匹配方法。通过对SCUT-IRAC手写体汉字库中的简单和较复杂手写体汉字识别进行的仿真实验结果表明,该方法具有接近人类识别汉字的容错性和准确性。
Applied Biomimetic Pattern Recognition to replace ＂ differentiation＂ of characteristic sample by machine ＂cognition＂, a novel method of handwritten Chinese characters recognition is presented. Double weights elliptical neurons are used to cover four basic kinds of handwritten Chinese characters stroke segment. The topological property among the stroke segment neurons is analyzed. Six styles of Chinese characters stroke with fault tolerance are combined. Imitated typing methods of human Chinese characters font code, the style, number, position and number of joint and crossover of stroke neurons which have redundant fault tolerant shapes are counted. A kind of characteristic knowledge data-base table of handwritten Chinese characters and the sample data-base of standard printed Chinese characters and fault tolerant matching rules are built. Simple and more complex handwritten Chinese characters in SCUT-IRAC HCCLIB are tested. The method is proved to be close to human fault tolerance and veracity.
出处
《中国图象图形学报》
CSCD
北大核心
2007年第7期1261-1269,共9页
Journal of Image and Graphics
关键词
仿生模式识别
神经元
特征知识
容错性
biomimetic pattern recognition, neuron, characteristic knowledge, fault tolerance
