Image Segmentation By Watersheds Using Analysis of Co - occurrence Matrix


The KIPS Transactions:PartB , Vol. 8, No. 1, pp. 59-65, Feb. 2001
10.3745/KIPSTB.2001.8.1.59,   PDF Download:

Abstract

Watershed transform has been used a powerful tool for image segmentation. However, this methods generally give rise to over-segmentation because of a many of local minima, and numerous techniques have been researched for an improvement. In this paper, we propose the automatic marker-based watershed algorithm that segments images by proceeding the extraction stage of markers that can get ride of irrelevant local minima, simultaneously selects and labels automatically markers consisting of sets of meaningful adjacent pixels and the extraction stage of watersheds that performs flooding and relabeling with markers. In other to present that a proposed algorithm reduced greatly over-segmented quantity, we test and analysis it by applying popular images and ICG retina images with powerful texture property to this algorithm.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
M. C. Lim and W. S. Kim, "Image Segmentation By Watersheds Using Analysis of Co - occurrence Matrix," The KIPS Transactions:PartB , vol. 8, no. 1, pp. 59-65, 2001. DOI: 10.3745/KIPSTB.2001.8.1.59.

[ACM Style]
Moon Cheol Lim and Woo Saeng Kim. 2001. Image Segmentation By Watersheds Using Analysis of Co - occurrence Matrix. The KIPS Transactions:PartB , 8, 1, (2001), 59-65. DOI: 10.3745/KIPSTB.2001.8.1.59.