Offline handwritten Tai Le character recognition using ensemble deep learning

Handwriting recognition is an important area in pattern recognition. For many years, Tai Le has been widely used in Southwest China and Southeast Asia, which makes it of great interest for recognition research. The characteristics of the highly similar characters in Tai Le, such as its large proport...

Full description

Saved in:
Bibliographic Details
Published in:The Visual computer 2022-11, Vol.38 (11), p.3897-3910
Main Authors: Guo, Hai, Liu, Yifan, Yang, Doudou, Zhao, Jingying
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Artificial neural networks
Character recognition
Classification
Computer Graphics
Computer Science
Datasets
Deep learning
Handwriting recognition
Image Processing and Computer Vision
Machine learning
National identity
Network management systems
Neural networks
Original Article
Pattern recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Handwriting recognition is an important area in pattern recognition. For many years, Tai Le has been widely used in Southwest China and Southeast Asia, which makes it of great interest for recognition research. The characteristics of the highly similar characters in Tai Le, such as its large proportion of similar characters and the randomness of its writing, bring great challenges to the task of recognition. In this paper, a method based on ensemble deep learning for offline handwritten Tai Le characters is proposed. First, the handwritten Tai Le character dataset SDH2019.2 was constructed and preprocessed. Then, an ensemble deep convolutional neural network (EDCNN) model was constructed by using a stacking strategy. Thirty deep neural network (DNN) and logistic regression algorithms were integrated into a strong Tai Le classifier by stacking. Experiments showed that the proposed model is competitive with the base DNN model and other ensemble models. The results indicate that the performance of Tai Le recognition by the stacking ensemble-based deep neural network model is high, with an accuracy of 98.85%. Additionally, its precision, recall and F1-score of 98.87%, 98.85% and 98.85%, respectively, are superior to those of other classic neural network models. To verify the general applicability of EDCNN, its effectiveness was also verified by recognizing MNIST handwritten digits and Devanagari handwritten characters.
ISSN:0178-2789
1432-2315
DOI:10.1007/s00371-021-02230-2