Naslov
Influence of image compression on segmentation of natural images

Autori
Gaši, Ana ; Dujmić, Hrvoje ; Turić, Hrvoje ; Papić, Vladan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 9th WSEAS International Conference on Signal Processing / Niola, V. - Sofija : Europment, 2010, 77-82

ISBN
978-954-92600-4-5

Skup
9th WSEAS International Conference on Signal Processing

Mjesto i datum
Catania, Italija, 29.05.2010. - 31.05.2010

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Image segmentation; compression; mean shift; search and rescue; object detection

Sažetak
One of important image processing applications is detection of humans for non-urban Search and Rescue. Authors have previously developed a method which, using mean shift segmentation, searches for objects (humans and artificial objects) in natural images. It is based on assumption that objects have different color comparing to the rest of image. Main problem in using mean shift algorithm is long processing time. In this paper, influence of image compression ratio on mean shift processing time as well as on detection results has been investigated. It is shown that increase in compression ratio results with shorter processing time while detection of objects (Recall and Precision) is not significantly deteriated.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA