A Wavelet-Based Descriptor for Handwritten Numeral Classification

In this work we propose descriptors for handwritten digit recognition based on multiresolution features by using the CDF 9/7 Wavelet Transform and Principal Component Analysis, in order to improve the classification performance and obtain a strong reduction on the size of the digit representation. This allows for a higher precision in the recognizers and, at the same time, lower training costs, especially for large datasets. Experiments were carried out with the CENPARMI and MNIST databases, widely used in the literature for this kind of problems, combining classifiers of the Support Vector Machine type. The recognition rates are good, comparable to those reported in previous works.