现代藏文基字识别的算法设计  

Designing Algorithm of the Modern Tibetan Base-word recognition

作　　者：拉巴顿珠[1] 欧珠[1] 

机构地区：[1]西藏大学藏文信息技术研究中心,西藏拉萨850000

出　　处：《西藏大学学报（社会科学版）》2016年第2期82-88,共7页Journal of Tibet University

基　　金：2014年度西藏自治区哲学社会科学基金项目"藏语言文字现代化与信息化研究"(项目号:14AYY001);2015年度西藏大学硕士研究生高水平人才培养项目"现代藏文基字识别的算法设计"阶段性成果

摘　　要：藏文基字是藏文字符的核心构件,能够在藏文音节结构中准确地识别基字,不仅有利于解析藏文字符的构件,对实现藏文排序算法也具有重要意义。文章依据藏文文法,严格遵循现代藏文音节字的结构特征,设计了现代藏文音节字的基字识别算法,并对不符合现代藏文构字规则的高频字进行了特殊处理,设计实现了现代藏文音节字的基字识别软件。该软件对18785个现代藏文音节字进行测试,识别率达到100%。Tibetan base word is the core component of Tibetan character. Accurate differentiation of Tibetanbase word in Tibetan syllable structure is not only beneficial to resolving the component of Tibetan character butalso it has important implication in realizing Tibetan ordering algorithms. The component of modern Tibetan syl-lables words was defined and recognizing algorithm of the base word of modern Tibetan syllables words was alsodesigned base on Tibetan grammar and strictly following with the structure characteristics of modern Tibetan syl-lable words. In addition, the words incompatible with the rules of modern Tibetan syllable word structure withhigh frequency were conducted special treatment. Base word character recognition software of modern Tibetansyllable words was designed and 18000 modern Tibetan syllable words were tested by the software and the wordrecognition rate reached up to100%.

关 键 词：藏文字处理 藏文基字 识别算法 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]