基于HMM的满文文本识别后处理的研究  

Research on the Post-processing of Manchu Character Recognition Based on Hidden Markov Model

作　　者：赵骥[1] 李晶皎[2] 王丽君[1] 张继生[1] 

机构地区：[1]鞍山科技大学计算机科学与工程学院,辽宁鞍山114044 [2]东北大学信息科学与工程学院,辽宁沈阳110004

出　　处：《中文信息学报》2006年第4期63-67,共5页Journal of Chinese Information Processing

基　　金：辽宁省自然科学基金资助项目(2001113)

摘　　要：将满文单词识别系统的识别信息和满文的词组信息有机的结合起来,建立满文词组和待定词集统计信息库,采用基于统计的隐马尔可夫模型的方法,依据贝叶斯准则,综合满文待定词的后验概率和词组的先验概率信息,建立合理有效便于实现的数据结构,采用动态规划法对满文单词识别系统输出存在的拒识词和错识词进行检测和纠正,从而有效的提高满文文本识别系统的识别率。实验表明:后处理性能除取决于语言模型外,还取决于概率的精确估计。另外,在单词识别系统识别率高的情况下,后处理的纠错能力会增强。The study pmpeses a post-processing method to improve the performance of Manchu character recognition. A evaluation model based on the Bayes rule are used to estimate the probability of the candidate Manchu words, which takes both the posterior probability of candidate and the prior probability of Manchu phrases into account. A Hidden Markov Model and Viterbi dynamic programming algorithm are adopted to check the output of the character recognition and to correct the rejected and mistaken words. This efficiently enhances the recognition rate of Manchu manuscript. The results indicate that the pest-processing performance depends on the language model and the accuracy of the evaluation model. Additionally, a higher recognition precision of SCR （Single Character Recogniton） will yield a better performance of error correction of post-processing.

关 键 词：计算机应用 中文信息处理 满文 后处理 模糊矩阵 贝叶斯准则 特征矢量 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]