基于部件组合的联机手写'藏文—梵文'样本生成

摘要

"藏文—梵文"包括500多个现代藏文、6000多个梵音藏文,在文字识别领域属于大类别的字符集,所以联机手写样本采集是庞大而复杂的工程.鉴于此,提供了一种基于部件组合的"藏文—梵文"手写样本生成方法,主要包括:(1)确定"藏文—梵文"字符集和部件集;(2)获取"藏文—梵文"字丁的部件位置信息;(3)采集联机手写"藏文—梵文"部件的样本;(4)生成联机手写"藏文—梵文"字符集样本库.该文为联机手写"藏文—梵文"识别的研究提供字符训练样本库和测试样本库,提高了手写梵音藏文样本采集效率,解决了样本数量及多样性问题,降低了样本采集成本,为进一步联机手写梵音藏文识别的研究与系统开发奠定了基础.%Tibetan-Sanskrit includes more than 500 Tibetan characters,and more than 6000 Sanskrit.Belonging to the large class of character set,the sample collection of the online handwritten is a large and complex project.We present an online handwriting character sample generation method based on component combination for Tibetan-San-skrit.The proposed method includes four main parts :(1) to determine the Tibetan-Sanskrit character set and com-ponent set ;(2) to get location information of Tibetan-Sanskrit characters ;(3) to collect online handwritten sample of component set for Tibetan-Sanskrit ;and (4) to generate sample database of online handwritten Tibetan-Sanskrit character set.This provides the character's training sample set and test sample set for online handwritten Tibetan-Sanskrit.