一种基于连体段的维吾尔文单词特征提取方法

A Uyghur Words Feature Extraction Method Based on the Conjoined Section

维吾尔新文字字符识别一般使用维度大的特征进行识别.这样的识别比较耗时,但识别精度较高.如果用维度小的特征进行识别,一般省时但是精度低.理想的识别不仅需要高速度还需要高精度.为解决此问题,本文选择直接对整体单词识别,避免每个字符识别完以后再整合成单词进行识别,为此选择连体段轮廓为主特征,进行特征提取,包括基线上的外轮廓.基线中的内轮廓和基线下的外轮廓.对于不能唯一识别的单词需要借助辅助特征进行二次识别.测试表明该方法不仅保证了小维度特征的速度,也发挥了高维度特征的识别精度.本系统识别率约为90%,同时它的平均识别时耗和速度也在实际需求的可接受范围之内.

Uyghur new text character recognition generally use the large dimension feature for the recognition work. This kind of recognition method will be more time-consuming, but the accuracy is often higher.Nevertheless, recognition based on small dimension feature can be more time-saving but lower evaluation accuracy. The ideal recognition requires not only a high speed but also need high accuracy. In order to solve this problem, this paper chose the whole word recognition method to avoid the shortcoming of word recognition after recognize each letter in the word. Therefore, this research selected outlines including outer contour on the baseline, the inner contour in the baseline and the outer contour behind the baseline as main feature to realize the feature extraction work. For the words that couldn＇t be recognized in a unique identification, the second recognition test using complimentary characteristics was carried out.After testing, this method not merely ensured the high speed of small dimension but also got high precision in high dimension. The experiment result shows that the recognition rate of this system is about 90%, and its average recognition time and its speed are in the acceptable range of the accrual requirements.