Off-line cursive script recognition: current advances, comparisons and remaining problems
Artificial Intelligence Review
| Hi-index | 0.00 |
This research proposes an approach to the analysis of contour characteristics for the feature extraction process of an off-line Thai handwritten character recognition system (THW-CR). The system aims at increasing the accuracy of both feature extraction rate and character recognition rate. We introduce the contour to capture the movement of features. The propose modules are the feature representation and the feature conflict resolution rules. With our proposed approach, the experiment shows the results increase reasonably. The maximum Feature Extraction Rate (FER) reached 97.73%. Meanwhile, the highest Character Recognition Rate (CRR) reached 95.35%. Additionally, the result of the overall evaluation showed that the THW-CR system generated reliable results for improving the accuracy of the feature extraction rate and the character recognition rate compared with the previous research by 3.62% and 8.33%, respectively.