| Autor: |
Antonio Berlanga, Juan Besada, Jesús Herrero, José Molina, Javier Portillo, José Casar |
| Zdroj: |
EURASIP Journal on Applied Signal Processing; Jul2004, Vol. 2004 Issue 8, p1125-1134, 10p |
| Abstrakt: |
The design of statistical classification systems foroptical character recognition (OCR) is a cumbersome task. Thispaper proposes a method using evolutionary strategies (ES) toevolve and upgrade the set of parameters in an OCR system. ThisOCR is applied to identify the tail number of aircrafts moving onthe airport. The proposed approach is discussed and some resultsare obtained using a benchmark data set. This researchdemonstrates the successful application of ES to a difficult,noisy, and real-world problem. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
