A nonlinear normalization method for handprinted kanji character recognition - line density equalization
A nonlinear normalization method for handprinted kanji character recognition - line density equalization
复制标题
DOI：
10.1016/0031-3203(90)90110-7
复制
发表时间：
1990-09
期刊：
影响因子：
--
通讯作者：
Hiromitsu Yamada;Kazuhiko Yamamoto;Taiichi Saito
中科院分区：
文献类型：
--
作者：
Hiromitsu Yamada;Kazuhiko Yamamoto;Taiichi Saito
提出了一种非线性归一化方法--“线密度均衡”法，即对局部线密度与采样间距的乘积进行均衡。因此，空间中的线密度被均匀化，空间的利用效率被提高，并且对于部分不规则的形状变化获得稳定的归一化。将该方法应用于手写体汉字识别中，取得了较好的识别效果。
A nonlinear normalization method, the “line density equalization”, is proposed, where a resampling is done so as to equate the product of a local line density and a (variable) sampling pitch. Consequently, the line density in the space is homogenized, the efficiency of utilization of the space is increased, and a stable normalization is obtained for partially irregular shape variations. The method was applied to handprinted Kanji character recognition, and its effectiveness has been demonstrated.