By Topic

A dynamic threshold edge-preserving smoothing segmentation algorithm for anterior chamber OCT images based on modified histogram

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Wenliang Du ; Faculty of Information Technology, Macau University of Science and Technology, Taipa, Macao SAR, China ; Xiaolin Tian ; Yankui Sun

In this paper, a dynamic threshold edge-preserving smoothing (DTEPS) segmentation algorithm based on histogram is presented for anterior chamber OCT images the algorithm defines two thresholds, one threshold is used to determine a region of interest (ROI) as the region of interest discrimination threshold (ROIDT). Another threshold defined as the noise threshold (NT) is to detect noise from the region of interest which is gotten by the ROIDT. The algorithm first selects ROIDT and NT using first-order difference and second-order difference of the smoothed histogram. Then, use them to segment the image. To test the segmentation effect basic mathematical morphology [4] and median filtering have been used to do further denoising on the segmented image and kirsch edge detection operator is selected to detect the edge of anterior chamber OCT image which has been denoised. To evaluate this proposed algorithm, experiments are performed on the anterior chamber OCT images. The results are compared with the segmentation algorithm of using global maximum variance threshold. Experimental results show that the algorithm proposed not only removed more noise but also preserved the edge of ROI better than the global maximum variance threshold (GMVT) segmentation algorithm.

Published in:

Image and Signal Processing (CISP), 2011 4th International Congress on  (Volume:2 )

Date of Conference:

15-17 Oct. 2011