|
Syllabus Line Segmentation from Palm Leaf Manuscripts using Vector Neural Network |
|---|---|
| รหัสดีโอไอ | |
| Creator | Nwe Nwe Soe |
| Title | Syllabus Line Segmentation from Palm Leaf Manuscripts using Vector Neural Network |
| Publisher | Faculyt of Informatics, Mahasarakham University |
| Publication Year | 2561 |
| Journal Title | Journal of Applied Informatics and Technology |
| Journal Vol. | 1 |
| Journal No. | 1 |
| Page no. | 7-19 |
| Keyword | Vector Neural Network (VNN), Syllabus Segmentation, Palm Leaf Manuscripts, q-valued dimensions |
| URL Website | https://ph01.tci-thaijo.org/index.php/jait/article/view/100481 |
| Website title | Journal of Applied Informatics and Technology |
| ISSN | 2586-8136 |
| Abstract | This paper offers finding the syllabus segmentations from palm leaf manuscripts. This system can be used to provide for enhancing palm leaf manuscripts are taken by high quality resolution digital camera. The Vector Neural Network is that object location can be determined by clustering points of interest and hierarchically forming candidate of palm leaf manuscript regions according to similarity and spatial proximity predicates. This system can be used to optimize two factors: RGB background colors and number of vertical lines or horizontal lines to choose candidate area. Moreover, Parametric Vector Neural Network performs better accuracy and less calculation time than other traditional methods. This system can be applied to segmentation of candidate area which includes text. The results of the research can be used as an input image to implement an OCR system to provide information of being existence for their related fields. Neural network ensemble techniques have been shown to be very accurate classification techniques. However, in some real-life applications, a number of classifiers required to achieve a reasonable accuracy is enormously large and hence very space consuming. This paper introduces special neural method, Vector Neural Network (VNN), which has great associative memory and high performance. Parametric VNN analyzed using various size of database having randomly created patterns, noise levels, and fixed q-dimensions. The result shows that it has capacity much greater than conventional Neural Networks |
