Investigation of Normalization Techniques and Their Impact on a Recognition Rate in Handwritten Numeral Recognition

• Authors: Wieslaw Chmielnicki , Katarzyna Stapor
• Languages of publication: PL

Abstracts

PL

This paper presents several normalization techniques used in handwritten numeral recognition and their impact on recognition rates. Experiments with five different feature vectors based on geometric invariants, Zernike moments and gradient features are conducted. The recognition rates obtained using combination of these methods with gradient features and the SVM-rbf classifier are comparable to the best state-of-art techniques.

Keywords

PL

handwritten numeral recognition, normalization techniques, SVM classifier, feature vectors, OCR, geometric invariants, Zernike moments, gradient features

• Publisher: [unknown2]
• Journal: Schedae Informaticae
• Year: 2010
• Volume: 19

Dates

published

2010

online

08 - 07 - 2015

Contributors

author

Wieslaw Chmielnicki

author

Katarzyna Stapor