Automated handwritten characters recognition based on a vector field

被引：0

作者：

Izumi, Tetsuya ^{[1
,2
]}

Hattori, Tetsuo ^{[1
,2
]}

Kitajima, Hiroyuki ^{[1
,2
]}

Yamasaki, Toshinori ^{[1
,2
]}

机构：

[1] Faculty of Engineering, Kagawa University, Takamatsu, Kagawa 761-0396

来源：

IEEJ Transactions on Electronics, Information and Systems | 2007年 / 127卷 / 04期

关键词：

Feature extraction; Fourier transform; Handwritten characters recognition; Pattern recognition; Vector field;

D O I：

10.1541/ieejeiss.127.489

中图分类号：

学科分类号：

摘要：

In order to obtain a low computational cost method for automatic handwritten characters recognition, this paper proposes a combined system of two rough classification methods based on features of a vector field: one is an autocorrelation matrix method, and another is a low frequency Fourier expansion method. In each method, the similarity is defined as a weighted sum of the squared values of the inner product between input pattern and the reference patterns that are normalized eigenvectors of KL (Karhunen-Loeve) expansion. This paper also describes a way of deciding the weight coefficients using Linear Regression Method, and shows the effectiveness of the proposed method by illustrating some experimentation results for 3036 categories of handwritten Japanese characters.

引用

页码：489 / 496+3

共 3 条

[1] Hattori T., Watanabe Y., Sanada H., Tezuka Y., Handwritten Characters Recognition Using Vector Field Matching Based on Chessboard Distance Distribution, IEICE Trans, J64-D, 12, pp. 1097-1104, (1912)
[2] Hattori T., Yamasaki T., Watanabe Y., Sanada H., Tezuka Y., Distance based vector field method for feature extraction of characters and figures, Proceedings of IEEE Systems, pp. 207-212, (1991)
[3] Izumi T., Hattori T., Kitajima H., Yamasaki T., Characters Recognition Method Based on Vector Field and Simple Linear Regression Model, Proc. IEEE International Symposium on Communications and Information Technologies 2004 (ISCIT, pp. 498-503, (2004)

← 1 →