Abstrakti
A problem of detecting textural areas in images corrupted by noise is considered. Detection is based on joint use of several local parameters calculated in scanning windows (blocks) of different size. Trained support vector machine (SVM) classifier is used for combining local parameters. Factors that influence detector performance are analyzed. It is shown that detector performance can be improved by taking into account information from classifier output for neighbor pixels.
| Alkuperäiskieli | Englanti |
|---|---|
| Otsikko | 2015 2nd International Scientific-Practical Conference Problems of Infocommunications Science and Technology, PIC S and T 2015 - Conference Proceedings |
| Kustantaja | IEEE |
| Sivut | 230-233 |
| Sivumäärä | 4 |
| ISBN (elektroninen) | 9789669751928 |
| DOI - pysyväislinkit | |
| Tila | Julkaistu - 14 jouluk. 2015 |
| OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisussa |
| Tapahtuma | 2nd International Scientific-Practical Conference Problems of Infocommunications Science and Technology, PIC S and T 2015 - Kharkiv, Ukraina Kesto: 13 lokak. 2015 → 15 lokak. 2015 |
Conference
| Conference | 2nd International Scientific-Practical Conference Problems of Infocommunications Science and Technology, PIC S and T 2015 |
|---|---|
| Maa/Alue | Ukraina |
| Kaupunki | Kharkiv |
| Ajanjakso | 13/10/15 → 15/10/15 |
!!ASJC Scopus subject areas
- Computer Science (miscellaneous)
- Computer Science Applications
Sormenjälki
Sukella tutkimusaiheisiin 'Texture detection in noisy images by combining several local parameters'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.Siteeraa tätä
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver