대한전자공학회:학술대회논문집 (Proceedings of the IEEK Conference)
- 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
- /
- Pages.283-286
- /
- 2001
Pseudo-Distance Map Based Watersheds for Robust Region Segmentation
- Jeon, Byoung-Ki (Electrical and Computer Engineering Division, POSTECH) ;
- Jang, Jeong-Hun (Electrical and Computer Engineering Division, POSTECH) ;
- Hong, Ki-Sang (Electrical and Computer Engineering Division, POSTECH)
- 발행 : 2001.09.01
초록
In this paper, we present a robust region segmentation method based on the watershed transformation of a pseudo-distance map (PDM). A usual approach for the segmentation of a gray-scale image with the watershed algorithm is to apply it to a gradient magnitude image or the Euclidean distance map (EDM) of an edge image. However, it is well known that this approach suffers from the oversegmentation of the given image due to noisy gradients or spurious edges caused by a thresholding operation. In this paper we show thor applying the watershed algorithm to the EDM, which is a regularized version of the EDM and is directly computed form the edgestrength function (ESF) of the input image, significantly reduces the oversegmentation, and the final segmentation results obtained by a simple region-merging process are more reliable and less noisy than those of the gradient-or EDM-based methods. We also propose a simple and efficient region-merging criterion considering both boundary strengths and inner intensities of regions to be merged. The robustness of our method is proven by testing it with a variety of synthetic and real images.
키워드