Abstract
In this paper, we present a novel approach to character recognition that utilizes Daubechies’ wavelet. In particular, the proposed approach reduces the dimensionality of a two-dimensional pattern by way of a ring-projection method, and thereafter, performs Daubechies’ wavelet transform on the derived one-dimensional pattern to generate a set of sub-patterns, namely, curves that are non-self-intersecting. Further from the resulting non-self-intersecting curves, feature vectors can be extracted.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the First International Conference on Multimodal Interface |
| Publisher | International Conference on Multimodal Interface |
| Pages | 215-220 |
| Number of pages | 6 |
| Publication status | Published - Oct 1996 |
| Event | 1st International Conference on Multimodal Interface, ICMI 1996 - Beijing, China Duration: 15 Oct 1996 → 17 Oct 1996 |
Conference
| Conference | 1st International Conference on Multimodal Interface, ICMI 1996 |
|---|---|
| Country/Territory | China |
| City | Beijing |
| Period | 15/10/96 → 17/10/96 |
User-Defined Keywords
- Wavelet transforms
- Dimension reduction
- Character recognition