The feature Combination Technique for Off-line Thai Character Recognition System
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Baseline detection for on-line cursive Thai handwriting recognition based on PCA
KICSS'10 Proceedings of the 5th international conference on Knowledge, information, and creativity support systems
| Hi-index | 0.00 |
This paper describes an algorithm for clustering free-style Thai handwritten character models. The algorithm groups the characters that have a similar structure. Firstly, the algorithm begins with the vertical stroke detection. The vertical stroke is an important Thai character structure. Secondly, the character area will be divided into 7 脳 10 blocks by using the stroke information. Then, the pixel distribution feature is calculated from each block. The features will be trained using backpropagation neural network. Finally, the confusion matrix will be used to analyze the result in a clustering process. The characters are divided into 21 groups and the accuracy of the clustered model is 97.60 percent.