Applied Computational Intelligence and Soft Computing / 2015 / Article / Tab 11 / Research Article
On the Performance Improvement of Devanagari Handwritten Character Recognition Table 11 Comparison of performance of proposed method with the previously reported results.
Dataset Approach used by previous reported results Feature used by previous reported results Classifier used by previous reported results Previously reported recognition percentage Recognition percentage of proposed method (direct pixel as features) Recognition percentage of proposed method (gradient feature) CPAR-2012 digit [17 ] Classifier combination (MV) Direct pixel + profile + gradient + wavelet transform CCN, FNN, PRN, KNN, FFT 97.87% (35000) 97.47 (35000) 98.07 (35000) CPAR-2012 character [9 ] Classifier combination (MV) Direct pixel + profile + Gradient + wavelet transform CCN, FNN, PRN, KNN, FFT 84.03% (79400) 82.79% (79400) 85.11 (79400) ISI devanagari digit [18 ] Feature combination PCA/MPCA + QTLR SVM 98.55% (3000) CMATER data ISI devanagari digit [16 ] Multistage classifier Wavelet Multistage MLPs 99.04 with 0.24% rejection 97.26 (22546) Full ISI Data 98.17 (22546) Full ISI Data ISI devanagari digit [7 ] Ensemble using AdaBoost Zernike moments MLPs 96.80 (single) (22546)
Abbreviations used in Table 11 are as follows: PCA: principal component analysis, KNN: K-nearest neighbor, FNN: feed-forward neural network, SVM: support vector machine, MLP: multilayer perceptron, CNN: cascade neural network, PRN: pattern recognition network, and FFT: function fitting neural network.