摘要
笔划代表着汉字的内部特征,笔划穿越次数是对笔划进行全穿越,反映了汉字的整体特征,全穿越在粗分时区分汉字的能力不是太强,增加了二级识别的工作量。除了提取笔划全穿越外还提取笔划半穿越,并把半穿越的次数进行重新组合形成新的特征值。把全穿越和半穿越结合起来作为汉字的特征值,对汉字进行粗分,粗分不能区分的汉字,采用四个角的能量值密度特征对汉字进行细分。实验结果表明了该方法的有效性。与单独使用全穿透方法相比,提出的方法在粗分时区分汉字的能力增强,减少了二级识别的工作量。
Strokes represent internal character of Chinese character, which can express the Chinese character topology features. The previous method of traversing times of strokes is full- breakthrough to stroke, but this method is not effective for some Chinese Characters, increase workload for second recognition. This paper introduces half- break-through of strokes, and constructs a new feature by using the times of half - breakthrough of strokes. It is used to implement the first recognition that the combination of full - breakthrough and half - breakthrough. The energy - density is used to do the second recognition for the Chinese Characters which can not be recognized in the first recognition. The experiment results show this method is effective. The new method enhances recognition capability in first recognition and decreases workload of the second recognition.
出处
《华北电力大学学报（自然科学版）》
CAS
北大核心
2008年第3期107-109,112,共4页
Journal of North China Electric Power University：Natural Science Edition
关键词
笔划
穿越次数
能量值
汉字识别
stroke
traversing times
energy
Chinese character recognition
