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.