Please use this identifier to cite or link to this item:
Publisher DOI: 10.1155/2013/593183
Title: Closed contour specular reflection segmentation in laparoscopic images
Language: English
Authors: Marcinczak, Jan Marek 
Grigat, Rolf-Rainer 
Issue Date: Aug-2013
Publisher: Hindawi Publishing Corporation
Source: Jan Marek Marcinczak and Rolf-Rainer Grigat, “Closed Contour Specular Reflection Segmentation in Laparoscopic Images,” International Journal of Biomedical Imaging, vol. 2013, Article ID 593183, 6 pages, 2013. doi:10.1155/2013/593183
Journal or Series Name: International journal of biomedical imaging 
Abstract (english): Segmentation of specular reflections is an essential step in endoscopic image analysis; it affects all further processing steps including segmentation, classification, and registration tasks. The dichromatic reflectance model, which is often used for specular reflection modeling, is made for dielectric materials and not for human tissue. Hence, most recent segmentation approaches rely on thresholding techniques. In this work, we first demonstrate the limited accuracy that can be achieved by thresholding techniques and propose a hybrid method which is based on closed contours and thresholding. The method has been evaluated on 269 specular reflections in 49 images which were taken from 27 real laparoscopic interventions. Our method improves the average sensitivityby 16% compared to the state-of-the-art thresholding methods.
DOI: 10.15480/882.1572
ISSN: 1687-4196
Institute: Bildverarbeitungssysteme E-2 
Type: (wissenschaftlicher) Artikel
Project: Open Access Publizieren 2013 - 2015 / Technische Universität Hamburg-Harburg 
License: CC BY 3.0 (Attribution) CC BY 3.0 (Attribution)
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
IJBI.2013.593183.pdf1,07 MBAdobe PDFThumbnail
Show full item record

Page view(s)

Last Week
Last month
checked on Sep 19, 2020


checked on Sep 19, 2020

Google ScholarTM


Note about this record


This item is licensed under a Creative Commons License Creative Commons