Analysis of continuous tracks of online aerial handwritten character recognition

被引:0
作者
Ogura, Kazutaka [1 ]
Nishida, Yoshihiro [1 ]
Miura, Hirokazu [2 ]
Matsuda, Noriyuki [2 ]
Taki, Hirokazu [2 ]
Abe, Norihiro [3 ]
机构
[1] Wakayama Univ, Grad Sch Syst Engn, Wakayama 6408510, Japan
[2] Wakayama Univ, Wakayama 6408510, Japan
[3] Kyushu Inst Technol, Fukuoka 8208502, Japan
来源
KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 3, PROCEEDINGS | 2008年 / 5179卷
关键词
black board model; dynamic programming; handwritten character; on-line character recognition; gyro sensor; motion vector;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper describes the on-line handwritten character recognition method in an arbitrary place without the information of up and down moving of the pen lifting. This method can be applied to the character interface (aerial handwritten character recognition device) with which the user moves the hand in the air. To realize the system, we selected the gyro sensor for the aerial handwritten character recognition device. This device can detect the moving direction. The advantage of this device is able to be used anytime and anywhere like a pen. It is not necessary to preparer the table in order to detect absolute position. We developed the blackboard model recognition system that includes 2 types DP matching recognition programs. The system is able to recognize the Japanese hiragana characters in 84% accuracy.
引用
收藏
页码:687 / +
页数:2
相关论文
共 33 条
[31]   A robust method for coarse classifier construction from a large number of basic recognizers for on-line handwritten Chinese/Japanese character recognition [J].
Zhu, Bilan ;
Nakagawa, Masaki .
PATTERN RECOGNITION, 2014, 47 (02) :685-693
[33]   ONLINE JAPANESE CHARACTER-RECOGNITION BASED ON FLEXIBLE PATTERN-MATCHING METHOD USING NORMALIZATION-COOPERATIVE FEATURE-EXTRACTION [J].
HAMANAKA, M ;
YAMADA, K ;
TSUKUMO, J .
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1994, E77D (07) :825-831