Naslov
Edge Detection by Using Focus of Attention Area

Autori
Ribarić, Slobodan ; Perković, Željka ; Pavešić, Nikola

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

Izvornik
Conference Proceeding of the 5th SCI'99 and ISAS'99 ; Volume 6 : Image, Acustic, Speech and Signal Processing / Torres, Michel ; Sanchez, Belkis ; D. G. Lainitis - : International Institute of Informatics and Systemics, USA, 1999, 163-169

ISBN
980-07-5919-0

Skup
International Conference on Information Systems Analysis and Synthesis

Mjesto i datum
Orlando (FL), Sjedinjene Američke Države, 31.07.1999. - 04.08.1999

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
image segmentation; edge detection; Split-and-merge; Canny edge operator; Focus of attention area

Sažetak
A method of image segmentation based on the composition of the Split-and- Merge method and the Canny edge operator is proposed in the paper. In order to speed-up the computationally intensive Canny operator, the proposed method applies preliminary region segmentation using the Split-and-Merge method for detecting uniform regions and bounderies among them. Based on the assumption that there is high probability of the existence of edges in areas thet are close to the bounderies of the regions, the strips around these bounderies are formed. These strips determine a (sub)field of the image called the focus of attention area. The Canny operator is only applied to the focus of attention area in the image. By navigating the Canny operator to the focus of attention area, the reduction of operations required for the edge detection is achieved.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA