Research Article
A New Dataset Size Reduction Approach for PCA-Based Classification in OCR Application
Table 3
Result comparison for handwritten Farsi/Arabic digit recognition.
| Year | References | Training dataset | Total number of testing samples | Number of features | Recognition time per sample (seconds) | Accuracy |
| 2013 | The proposed method | Hoda (40,000 samples) | 20,000 | 79 | 0.036810 | 96.02% | 2011 |
Enayatifar and Alirezanejad [32] | Hoda (40,000 samples) | 20,000 | 48 | (Not reported) | 92.70% | 2013 | The proposed method | Hoda (7,000 samples) | 3000 | 79 | 0.046235 | 95.72% | 2011 |
Enayatifar and Alirezanejad [32] | Hoda (7,000 samples) | 3000 | 48 | 0.21 | 94.30% |
|
|