Abstract
The problem of the automatic recognition of unconstrained handwritten mail is discussed. Our approach combines statistical and structural techniques. The statistical stage is the first and main stage of our recognition system. It uses concavity measurements to characterize the characters and a linear discrimination technique is implemented to affect one character to one cluster. The second stage, called structural supervisor, was developed in order to control and improve the results of the first stage.
| Original language | English |
|---|---|
| Pages (from-to) | 217-221 |
| Number of pages | 5 |
| Journal | IEE Conference Publication |
| Issue number | 307 |
| Publication status | Published - 1 Dec 1989 |
| Externally published | Yes |
| Event | Third International Conference on Image Processing and its Applications - Coventry, Engl Duration: 18 Jul 1989 → 20 Jul 1989 |