Abstract
A novel border-following algorithm is used to reconstruct the borders and missing links of noisy and broken handwritten digits. When combined with a suitable rejection threshold, improved performance from handwritten character classifiers is achieved. Experimental results are given which show the effectiveness of the method, raising recognition rates by an additional 5% for handwritten digits in the presence of gaps and noise. Copyright © 1996 Pattern Recognition Society. Published by Elsevier Science Ltd.
| Original language | English |
|---|---|
| Pages (from-to) | 1429-1435 |
| Journal | Pattern Recognition |
| Volume | 29 |
| Issue number | 8 |
| DOIs | |
| Publication status | Published - Aug 1996 |
| Externally published | Yes |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 3 Good Health and Well-being
Research Keywords
- Border linking
- Boundary tracing
- Broken character strokes
- Handwritten character recognition
- Image thresholding
- Segmentation
Fingerprint
Dive into the research topics of 'Linking broken character borders with variable sized masks to improve recognition'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver