基于动态规划的联机手写汉字分割方法

为解决手写汉字文本的自动切分问题,提出了一种基于动态规划的联机手写汉字分割方法.该方法根据手写笔画的结构特征、笔顺信息以及神经网络分类器给出的类概率构造代价函数,并将其分别应用于手写句子的预分割和基于识别的分割过程,然后利用动态规划算法寻找最佳分割路径.预分割在保持较低误分割率的前提下,可以有效地降低候选分割块的数量,以加速分割过程.实验结果表明,预分割的误分割率为0.57%,过分割率仅为11.1%;在未应用语言模型的情况下,最终的正确分割率为88.2%.

Dynamic Programming-Based Online Handwritten Chinese Character Segmentation Approach

In order to solve the problem of automatic segmentation of handwritten Chinese text,a dynamic programming-based online handwritten Chinese character segmentation method is proposed.In this method,the geometrical features of handwritten strokes,the stroke sequence information and the class probability given by the neural network classifier are used to construct a segmentation cost function,and are then applied to the pre-segmentation and recognition-based segmentation stages of handwritten sentences,respectively.After that,the dynamic programming algorithm is adopted to find the optimal segmentation path.The pre-segmentation can effectively reduce the amount of segmentation hypothesis with a reasonable incorrect segmentation rate,thus speeding up the segmentation.Experimental results show that the pre-segmentation stage achieves an incorrect segmentation rate of 0.57% and an over-s egmentation rate of 11.1%,and that the final correct segmentation rate is 88.2% without using any language model.