Chinese handwritten character segmentation in form documents

檔案

本條目沒有附加檔案。

日期

1999

期刊名稱

DOCUMENT ANALYSIS SYSTEMS: THEORY AND PRACTICE

卷期與頁次

第 1655 卷,頁 348–362

ISSN

0302-9743

ISBN

3-540-66507-2

語言

英文

摘要

This paper presents a projection based method for segmenting handwritten Chinese characters in form documents with known structures. In the preprocessing phase, a noise removal method is proposed that preserves stroke connections and character edge points. In the character segmentation phase, the projection profile analysis method is used to segment a text line image into projection blocks. In addition, projection blocks are classified into one of four types: mark, half-word, single-word, and two-word. Large blocks are then split and small blocks are merged. In addition, an OCR system is adopted to eliminate errors resulting from the inappropriate merging of Chinese numerical characters with other characters. As for 1319 Chinese characters are tested during our experiments, the correct segmentation rates of 92.34% and 91.76% are obtained with and without the OCR module.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Chen, J., Wu, C., & Lee, H. (1999). Chinese handwritten character segmentation in form documents. DOCUMENT ANALYSIS SYSTEMS: THEORY AND PRACTICE, 1655, 348–362. https://ir.lib.nycu.edu.tw/handle/11536/31670

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/31670