利用上下文相关信息的汉字文本识别

Chinese Text Recognition Using Contextual Information

为了改善汉字文本识别率，本文提出了一种基于语料库统计概率的后处理方法，该方法利用上下文相关信息，超过词汇。对于汉字文本识别，把具有确定性边界的一个汉字序列（多数情况为一个句子）作为一个处理单元，利用统计获得的字字同现概率，采用动态规划方法，获得了令人满意的效果。

In order to improve Chinese text recognition rate, in this paper we present a post processing method of corpus-based statistical probabilities. The method has used contextual information more than the lexical lever knowledge. For Chinese text recognition, a bounded seguence of Chinese characters (more often, a sentence) is processed as an unit. And the cooccurrence probability between characters and dynamic progamming strategy are employed to acquire the satisficatory recognition results.