Identifying Handwritten Text in Mixed Documents

Author

Farooq, Faisal ; Sridharan, Karthik ; Govindaraju, Vengatesan

Author_Institution

CEDAR, Buffalo Univ., Amherst, NY

Volume

2

fYear

0

fDate

0-0 0

Firstpage

1142

Lastpage

1145

Abstract

In this paper we present a system for classification of machine printed and handwritten text in mixed documents. The classification is performed at the word level. We propose a feature extraction algorithm for each word image based on Gabor filters followed by classification using an expectation maximization (EM) based probabilistic neural network that reduces overfitting of training data. An overall precision of 94.62% was obtained for the Arabic script using the modified neural network. The accuracies obtained using a simple backpropagation neural network and an SVM were 83.33% and 90.26% respectively

Keywords

Gabor filters; backpropagation; document image processing; expectation-maximisation algorithm; feature extraction; handwriting recognition; image classification; neural nets; probability; support vector machines; Arabic script; Gabor filters; SVM; backpropagation neural network; expectation maximization; feature extraction; handwritten text identification; machine printed classification; modified neural network; probabilistic neural network; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.676

Filename

1699411