Research Article
Script Identification from Printed Indian Document Images and Performance Evaluation Using Different Classifiers
Table 2
Comparison of result for different classifiers: AAR: average accuracy rate, MBT: model building time.
| Type | Classifier | AAR (%) | MBT (s) |
| Bayesian | BayesNet | 96.7 | 0.09 |
| Functional | LibLINEAR | 97.6 | 0.38 | MLP | 98.4 | 35.3 | RBFNetwork | 95.6 | 5.9 | Simple Logistic | 98.9 | 8.36 |
| Rule based | FURIA | 93.8 | 0.69 | PART | 91.7 | 0.19 |
| Tree based | NBTree | 93.8 | 31.01 | Random Forest | 98.2 | 0.09 |
|
|