Machine printed handwritten text discrimination using Radon transform and SVM classifier

Author

Zemouri, ET-Tahir ; Chibani, Youcef

Author_Institution

Signal Process. Lab., Univ. of Sci. & Technol. Houari Boumediene, Algiers, Algeria

fYear

2011

fDate

22-24 Nov. 2011

Firstpage

1306

Lastpage

1310

Abstract

Discrimination of machine printed and handwritten text is deemed as major problem in the recognition of the mixed texts. In this paper, we address the problem of identifying each type by using the Radon transform and Support Vector Machines, which is conducted at three steps: preprocessing, feature generation and classification. New set of features is generated from each word using the Radon transform. Classification is used to distinguish printed text from handwritten. The proposed system is tested on IAM databases. The recognition rate of the proposed method is calculated to be over 98%.

Keywords

Radon transforms; feature extraction; handwritten character recognition; image recognition; pattern classification; support vector machines; text analysis; IAM databases; Radon transform; SVM classifier; feature generation; machine printed handwritten text discrimination; mixed text recognition; support vector machines; Image segmentation; Kernel; Pattern recognition; Shape; Support vector machines; Transforms; Vectors; Radon transform; Support Vector Machines (SVM); document analysis; machine printed and handwritten text discrimination;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems Design and Applications (ISDA), 2011 11th International Conference on

Conference_Location

Cordoba

ISSN

2164-7143

Print_ISBN

978-1-4577-1676-8

Type

conf

DOI

10.1109/ISDA.2011.6121840

Filename

6121840