Discrete Wavelet-Based Multi-Classifier Approach for Recognition of Offline Handwritten Hindi Numerals

Abstract

The challenges and broad application fields related to handwritten numeral recognition, attract the research communities for further development. The major challenges one has to face for developing such systems are writing practices of individuals, degree of similarity in various digit shapes, and typical structure of digits written in Hindi script. The proposed model is designed to face these challenges by implementing effective feature extraction and classification methods. The model exploited bi-orthogonal Discrete Wavelet Transform (DWT) for important feature extraction and multiple classifiers, namely, Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the classification task. The proposed model not only recognized the handwritten numerals quite accurately, but was also successful in reducing the size of original features to release computational loads of classifiers. The scheme has managed to attain recognition accuracies of 96.64, 99.84, and 97.04% by the mentioned classifiers, respectively.