Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Digital Image Processing for OphthalmologyDetection of Geometrical Patterns

Digital Image Processing for Ophthalmology: Detection of Geometrical Patterns [The images in the DRIVE and STARE datasets are provided in the [R, G, B] format, where R, G, and B are the red, green, and blue components, respectively, of the color image. In the present work, after normalizing each component of the original color image (dividing by 255), the result was converted to the luminance component Y, computed as Y = 0.299R + 0.587G + 0.114B.The effective region of the image was thresholded using the normalized threshold of 0.1 for the DRIVE images and 0.15 for the STARE images; the thresholds were determined by experimentation with several images from each dataset. The artifacts present in the thresholded results on the edges were removed by applying morphological opening and erosion filters. A mask was generated with the obtained effective region.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Digital Image Processing for OphthalmologyDetection of Geometrical Patterns

Download PDF
21 pages

Loading next page...
 
/lp/springer-journals/digital-image-processing-for-ophthalmology-detection-of-geometrical-2h0asD1cIs

References (0)

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Springer International Publishing
Copyright
© Springer Nature Switzerland AG 2011
ISBN
978-3-031-00521-3
Pages
15 –36
DOI
10.1007/978-3-031-01649-3_3
Publisher site
See Chapter on Publisher Site

Abstract

[The images in the DRIVE and STARE datasets are provided in the [R, G, B] format, where R, G, and B are the red, green, and blue components, respectively, of the color image. In the present work, after normalizing each component of the original color image (dividing by 255), the result was converted to the luminance component Y, computed as Y = 0.299R + 0.587G + 0.114B.The effective region of the image was thresholded using the normalized threshold of 0.1 for the DRIVE images and 0.15 for the STARE images; the thresholds were determined by experimentation with several images from each dataset. The artifacts present in the thresholded results on the edges were removed by applying morphological opening and erosion filters. A mask was generated with the obtained effective region.]

Published: Jan 1, 2011

There are no references for this article.