|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
The offline handwritten text recognition is critical tasks, which need to be accomplished to move towards a paperless environment. In this paper, a hybrid handwritten text recognition system is proposed using Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In the proposed system, IAM dataset is used for training and testing. Totally 87,292 images are used for training and 4,316 images are used for testing. In the proposed system, five distinct features are extracted from the database. In this system, two different classifiers are used for classification namely CNN and RNN. The results obtained are shown in the paper. From the result, RNN performs better than CNN.
Keyword
Hybrid handwritten text recognition, IAM dataset, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN).
PDF Download (click here)
|
|
|
|
|