Browse > Article
http://dx.doi.org/10.7780/kjrs.2002.18.2.107

Remote Sensing Image Segmentation by a Hybrid Algorithm  

예철수 (서강대학교 전자공학과)
이쾌희 (서강대학교 전자공학과)
Publication Information
Korean Journal of Remote Sensing / v.18, no.2, 2002 , pp. 107-116 More about this Journal
Abstract
A hybrid image segmentation algorithm is proposed which integrates edge-based and region-based techniques through the watershed algorithm. First, by using mean curvature diffusion coupled to min/max flow, noise is eliminated and thin edges are preserved. After images are segmented by watershed algorithm, the segmented regions are combined with neighbor regions. Region adjacency graph (RAG) is employed to analyze the relationship among the segmented regions. The graph nodes and edge costs in RAG correspond to segmented regions and dissimilarities between two adjacent regions respectively. After the most similar pair of regions is determined by searching minimum cost RAG edge, regions are merged and the RAG is updated. The proposed method efficiently reduces noise and provides one-pixel wide, closed contours.
Keywords
Image Segmentation; Watershed Algorithm; Mean Curvature Diffusion; Region Adjacency Graph;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Hierarchy in picture segmentation: A stepwise optimization approach /
[ Beaulieu, J.;M. Goldberg ] / IEEE Trans. Pattern Anal. Machine Intell.
2 Image segmentation and analysis via multiscale gradient watershed hierarchies /
[ Gauch, J.M. ] / IEEE Trans. Image Processing
3 High precision photogrammetric data set for building reconstruction and terrain modeling /
[ Mason S.;E. Baltsavias;D. Stallmann ] / Internal Report
4 Watersheds in digital spaces: An efficient algorithm based on immersion simulations /
[ Vincent, L.;P. Soile ] / IEEE Trans. Pattern Anal. Machine Intell.
5 Hybrid image segmentation using watershed and fast region merging /
[ Haris K.;S.N. Efstratiadis;N. Maglaveras;A.K. Katsaggelos ] / IEEE Trans. Image Processing
6 Anisotropic diffusion for building segmentation from aerial imagery /
[ Ye, C.S.;K.H. Lee ] / Proc. of International Symposium on Remote Sensing, EMSEA and KSRS