A MDRNN-SVM hybrid model for cursive offline handwriting recognition

Authors:
Byron Leite Dantas Bezerra;Cleber Zanchettin;Vinícius Braga de Andrade
Affiliations:
Polytechnic School of Pernambuco, University of Pernambuco, Recife, PE, Brazil;Center of Informatics, Federal University of Pernambuco, Recife, PE, Brazil;Polytechnic School of Pernambuco, University of Pernambuco, Recife, PE, Brazil
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 13
Cited 0

The State of the Art in Online Handwriting Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Character Feature Extraction Using Polygonal Projection Sweep (Contour Detection)

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach
An Hybrid MLP-SVM Handwritten Digit Recognizer

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Recognition of Cursive Roman Handwriting - Past, Present and Future

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Long Short-Term Memory

Neural Computation
A SVM-based cursive character recognizer

Pattern Recognition
Character Recognition Using Hierarchical Vector Quantization and Temporal Pooling

AI '08 Proceedings of the 21st Australasian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
ICDAR 2009 Online Arabic Handwriting Recognition Competition

ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Multi-dimensional recurrent neural networks

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Handwritten character recognition through two-stage foreground sub-sampling

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a recurrent neural networks applied to handwriting character recognition. The method Multi-dimensional Recurrent Neural Network is evaluated against classical techniques. To improve the model performance we propose the use of specialized Support Vector Machine combined whit the original Multi-dimensional Recurrent Neural Network in cases of confusion letters. The experiments were performed in the C-Cube database and compared with different classifiers. The hierarchical combination presented promising results.