Feature Extraction and Selection in Batak Toba Handwritten Text Recognition
| Main Authors: | Pasaribu, Novie Theresia Br., Hasugian, Meilan Jimmy |
|---|---|
| Format: | Article PeerReviewed Book |
| Terbitan: |
, 2020
|
| Subjects: | |
| Online Access: |
http://repository.maranatha.edu/27998/1/IJAI-a-Pasaribu%20-%20final%20revision.pdf http://repository.maranatha.edu/27998/ |
Daftar Isi:
- Batak Toba is one of the tribes in Indonesia that has its own language and alphabet. However, not many Batak Toba people are familiar with the alphabet. In this paper, we use several feature extraction methods in the recognition process of Batak Toba handwritten text. For some features, between/within-class scatter matrix criterion is used to select the significant features. The k-NN classifier is used in the recognition step. The results show that elliptic Fourier descriptor is the most superior features that has recognition percentage greater than the other categories.