文章基本信息

标题：Preprocessing Model of Manuscripts in Javanese Characters
本地全文：下载
作者：Anastasia Rita Widiarti 1 , Agus Harjoko 2 , Marsono 3 , Sri Hartati
期刊名称：Journal of Signal and Information Processing
印刷版ISSN：2159-4465
电子版ISSN：2159-4481
出版年度：2014
卷号：05
期号：04
页码：112-122
DOI：10.4236/jsip.2014.54014
语种：English
出版社：Scientific Research Publishing
摘要：Manuscript preprocessing is the earliest stage in transliteration process of manuscripts in Javanese scripts. Manuscript preprocessing stage is aimed to produce images of letters which form the manuscripts to be processed further in manuscript transliteration system. There are four main steps in manuscript preprocessing, which are manuscript binarization, noise reduction, line segmentation, and character segmentation for every line image produced by line segmentation. The result of the test on parts of PB.A57 manuscript which contains 291 character images, with 95% level of confidence concluded that the success percentage of preprocessing in producing Javanese character images ranged 85.9% - 94.82%.
关键词：Binarization; Characters Segmentation; Line Segmentation; Noise Reduction; Manuscript Image Preprocessing