Research Article
Context-Aware Handwritten and Optical Character Recognition Using a Combination of Wavelet Transform, PCA and Neural Networks
470 downloads
@INPROCEEDINGS{10.1007/978-3-319-29236-6_25, author={Ngoc Phan and Thi Bui}, title={Context-Aware Handwritten and Optical Character Recognition Using a Combination of Wavelet Transform, PCA and Neural Networks}, proceedings={Context-Aware Systems and Applications. 4th International Conference, ICCASA 2015, Vung Tau, Vietnam, November 26-27, 2015, Revised Selected Papers}, proceedings_a={ICCASA}, year={2016}, month={4}, keywords={Character recognition Wavelet transform PCA Neural network Image processing}, doi={10.1007/978-3-319-29236-6_25} }- Ngoc Phan
Thi Bui
Year: 2016
Context-Aware Handwritten and Optical Character Recognition Using a Combination of Wavelet Transform, PCA and Neural Networks
ICCASA
Springer
DOI: 10.1007/978-3-319-29236-6_25
Abstract
This paper proposes a novel context-aware handwritten and optical character recognition algorithm using a combination of wavelet transform, PCA and neural networks. At first, the features of character are extracted using combination of wavelet transform and PCA. Then multi-layer feed-forward neural networks will be used to classify these extracted features. In this algorithm, we use one neural network for each training character. This neural network is used to determine whether an input character is training character or not. The paper experimental results show that the proposed algorithm gives an effective performance of character recognition on noisy images and competes with state-of-the-art algorithms.
Copyright © 2015–2024 ICST
