Segmentation of Touching Handwritten Digits Using Self-Organizing Maps

Author

Lacerda, Everton B. ; Mello, Carlos A B

Author_Institution

Center for Inf., Fed. Univ. of Pernambuco, Recife, Brazil

fYear

2011

fDate

7-9 Nov. 2011

Firstpage

134

Lastpage

137

Abstract

This paper presents a new algorithm for segmentation of touching handwritten digits. The proposal is divided into two parts: the selection of feature points which is made after the application of skeletonization, and the use of Self-Organizing Maps to define the segmentation points. As these two parts are independent from each other, the method is suitable for parallelization, increasing its performance. The algorithm was tested in a set of 42 images of real digits synthetically connected and achieved very promising results.

Keywords

document image processing; handwritten character recognition; image segmentation; image thinning; self-organising feature maps; document processing; feature point selection; self-organizing maps; touching handwritten digit segmentation; Algorithm design and analysis; Character recognition; Image recognition; Image segmentation; Proposals; Self organizing feature maps; Skeleton; connected handwritten digits; document processing; segmentation; self-organizing maps;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools with Artificial Intelligence (ICTAI), 2011 23rd IEEE International Conference on

Conference_Location

Boca Raton, FL

ISSN

1082-3409

Print_ISBN

978-1-4577-2068-0

Electronic_ISBN

1082-3409

Type

conf

DOI

10.1109/ICTAI.2011.28

Filename

6103317