1.
2.
| Received
04-Jun-2026 |
Accepted
- |
Published
04-Jun-2026 |
Abstract
Character recognition is major research area since its inspiration. So, far very limited progress has been made in it, specifically for Indian languages. Recognition of Gujarati script is a less studied area and no significant attempt is made so far to recognize Gujarati glyphs. In this paper we have presented a simple yet robust solution for recognition of offline multi-font computer generated and machine printed Gujarati Numerals. Pursued by the pre-processing techniques, we used a method called correlation based template matching where a numeral is identified by analyzing its shape and comparing its features that distinguish each numeral. The system appears to be very robust against font variations and large shape variations.
Keywords: Template, Correlation, Segmentation, Normalization, Probability, etc.
Locked
Subscribed
Open Access
Open Access