Wavelet-based feature extraction for handwritten numerals
We present a novel preprocessing technique for handwritten numerals recognition, that relies on the extraction of multiscale features to characterize the classes. These features are obtained by means of different continuous wavelet transforms, which behave as scale-dependent bandpass filters, and gi...
| Autores principales: | , , |
|---|---|
| Formato: | SER |
| Materias: | |
| Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_03029743_v5716LNCS_n_p374_Romero |
| Aporte de: |
| id |
todo:paper_03029743_v5716LNCS_n_p374_Romero |
|---|---|
| record_format |
dspace |
| spelling |
todo:paper_03029743_v5716LNCS_n_p374_Romero2023-10-03T15:19:09Z Wavelet-based feature extraction for handwritten numerals Romero, D. Ruedin, A. Seijas, L. Continuous Wavelet Transform Dimensionality Reduction Handwritten Numerals Pattern Recognition Complementary features Continuous Wavelet Transform Different scale Dimensionality reduction Handwritten numeral Handwritten Numerals Local orientations Multi layer perceptron Multi-scale features Neural network classifier Preprocessing techniques Recognition rates Shape-preserving Testing sets Wavelet-based Feature Bandpass filters Character recognition Feature extraction Image analysis Neural networks Wavelet transforms We present a novel preprocessing technique for handwritten numerals recognition, that relies on the extraction of multiscale features to characterize the classes. These features are obtained by means of different continuous wavelet transforms, which behave as scale-dependent bandpass filters, and give information on local orientation of the strokes. First a shape-preserving, smooth and smaller version of the digit is extracted. Second, a complementary feature vector is constructed, that captures certain properties of the digits, such as orientation, gradients and curvature at different scales. The accuracy with which the selected features describe the original digits is assessed with a neural network classifier of the multilayer perceptron (MLP) type. The proposed method gives satisfactory results, regarding the dimensionality reduction as well as the recognition rates on the testing sets of CENPARMI and MNIST databases; the recognition rate being 92.60 % for the CENPARMI data-base and 98.22 % for the MNIST database. © 2009 Springer Berlin Heidelberg. Fil:Ruedin, A. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Seijas, L. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. SER info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_03029743_v5716LNCS_n_p374_Romero |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
Continuous Wavelet Transform Dimensionality Reduction Handwritten Numerals Pattern Recognition Complementary features Continuous Wavelet Transform Different scale Dimensionality reduction Handwritten numeral Handwritten Numerals Local orientations Multi layer perceptron Multi-scale features Neural network classifier Preprocessing techniques Recognition rates Shape-preserving Testing sets Wavelet-based Feature Bandpass filters Character recognition Feature extraction Image analysis Neural networks Wavelet transforms |
| spellingShingle |
Continuous Wavelet Transform Dimensionality Reduction Handwritten Numerals Pattern Recognition Complementary features Continuous Wavelet Transform Different scale Dimensionality reduction Handwritten numeral Handwritten Numerals Local orientations Multi layer perceptron Multi-scale features Neural network classifier Preprocessing techniques Recognition rates Shape-preserving Testing sets Wavelet-based Feature Bandpass filters Character recognition Feature extraction Image analysis Neural networks Wavelet transforms Romero, D. Ruedin, A. Seijas, L. Wavelet-based feature extraction for handwritten numerals |
| topic_facet |
Continuous Wavelet Transform Dimensionality Reduction Handwritten Numerals Pattern Recognition Complementary features Continuous Wavelet Transform Different scale Dimensionality reduction Handwritten numeral Handwritten Numerals Local orientations Multi layer perceptron Multi-scale features Neural network classifier Preprocessing techniques Recognition rates Shape-preserving Testing sets Wavelet-based Feature Bandpass filters Character recognition Feature extraction Image analysis Neural networks Wavelet transforms |
| description |
We present a novel preprocessing technique for handwritten numerals recognition, that relies on the extraction of multiscale features to characterize the classes. These features are obtained by means of different continuous wavelet transforms, which behave as scale-dependent bandpass filters, and give information on local orientation of the strokes. First a shape-preserving, smooth and smaller version of the digit is extracted. Second, a complementary feature vector is constructed, that captures certain properties of the digits, such as orientation, gradients and curvature at different scales. The accuracy with which the selected features describe the original digits is assessed with a neural network classifier of the multilayer perceptron (MLP) type. The proposed method gives satisfactory results, regarding the dimensionality reduction as well as the recognition rates on the testing sets of CENPARMI and MNIST databases; the recognition rate being 92.60 % for the CENPARMI data-base and 98.22 % for the MNIST database. © 2009 Springer Berlin Heidelberg. |
| format |
SER |
| author |
Romero, D. Ruedin, A. Seijas, L. |
| author_facet |
Romero, D. Ruedin, A. Seijas, L. |
| author_sort |
Romero, D. |
| title |
Wavelet-based feature extraction for handwritten numerals |
| title_short |
Wavelet-based feature extraction for handwritten numerals |
| title_full |
Wavelet-based feature extraction for handwritten numerals |
| title_fullStr |
Wavelet-based feature extraction for handwritten numerals |
| title_full_unstemmed |
Wavelet-based feature extraction for handwritten numerals |
| title_sort |
wavelet-based feature extraction for handwritten numerals |
| url |
http://hdl.handle.net/20.500.12110/paper_03029743_v5716LNCS_n_p374_Romero |
| work_keys_str_mv |
AT romerod waveletbasedfeatureextractionforhandwrittennumerals AT ruedina waveletbasedfeatureextractionforhandwrittennumerals AT seijasl waveletbasedfeatureextractionforhandwrittennumerals |
| _version_ |
1807322464623001600 |