An on-line handwriting character recognition algorithm. RAV (reparameterized angle variations)

Proceedings of the Fourth International Conference on Document Analysis and Recognition Pub Date : 1997-08-18 DOI:10.1109/ICDAR.1997.620645

S. Masaki, M. Kobayashi, O. Miyamoto, Y. Nakagawa, T. Matsumoto

引用次数: 14

Abstract

A new algorithm RAV (Reparameterized Angle Variations) is proposed which makes explicit use of trajectory information where the time evolution of the pen coordinates plays a crucial role. The algorithm is extremely robust against stroke connections ("Tsuzukeji") as well as shape distortions ("Kuzushi-ji"). Preliminary experiments are reported on tests against the Kuchibue.d-96-02 data base from Tokyo University of Agriculture and Technology.

查看原文本刊更多论文

一个在线手写字符识别算法。再参数化角度变化

提出了一种明确利用轨迹信息的新算法RAV (Reparameterized Angle variation)，其中笔坐标的时间演化起着至关重要的作用。该算法对笔画连接(“Tsuzukeji”)和形状扭曲(“Kuzushi-ji”)具有极强的鲁棒性。报告了针对Kuchibue的初步试验。东京农业技术大学d-96-02数据库。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings of the Fourth International Conference on Document Analysis and Recognition

自引率

0.00%

发文量