Sciweavers

CRV
2005
IEEE

Segmentation of Laparoscopic Images: Integrating Graph-Based Segmentation and Multistage Region Merging

14 years 1 months ago
Segmentation of Laparoscopic Images: Integrating Graph-Based Segmentation and Multistage Region Merging
This paper presents a method that combines graphbased segmentation and multistage region merging to segment laparoscopic images. Starting with image preprocessing, including Gaussian smoothing, brightness and contrast enhancement, and histogram thresholding, we then apply an efficient graph-based method to produce a coarse segmentation of laparoscopic images. Next, regions are further merged in a multistage process based on features like grey-level similarity, region size and common edge length. At each stage, regions are merged iteratively according to a merging score until convergence. Experimental results show that our approach can achieve good spatial coherence, accurate edge location and appropriately segmented regions in real surgical images.
Yueyun Shu, Guillaume-Alexandre Bilodeau, Farida C
Added 13 Oct 2010
Updated 13 Oct 2010
Type Conference
Year 2005
Where CRV
Authors Yueyun Shu, Guillaume-Alexandre Bilodeau, Farida Cheriet
Comments (0)