Table 12 Comparison with other methods using feature selection
From: A hybrid recognition system for off-line handwritten characters
Authors | Dataset | Feature extraction method | Feature selection | Classifier | % Accuracy capital alphabet | % Accuracy small alphabet |
|---|---|---|---|---|---|---|
Chung and Yoon (1997) | NIST | Gradient | PCA | Neural network | 93.31 | – |
UDLRH | 90.85 | – | ||||
De Stefano et al. (2013) | NIST | Hybrid features | GA | SVM | 57.88 | Â |
MLP | 62.57 | Â | ||||
KNN | 61.45 | Â | ||||
Proposed method | CEDAR | Hybrid features | GA | MLP NN | 94.65 | 91.11 |