 |
Interactive Tutorials
Segmentation (Image Outlining)
Image outlining (or segmentation) is an algorithm that can be utilized to detect and enhance the boundaries of features appearing in a grayscale or binary digital image. The manipulated image produced by the algorithm is useful for accurately measuring and classifying features and details appearing in the original specimen.
The tutorial initializes with a randomly selected specimen (captured in the microscope) appearing in the left-hand window entitled Specimen Image. To the right of the Specimen Image window is an Image Histogram graph that displays the gray-level histogram of the digital image obtained from the microscope. To operate the tutorial, select a specimen image from the Choose a Specimen pull-down menu, and use the Erosion Iterations and Dilation Iterations sliders to adjust the number of times the erosion and dilation algorithms are applied to the specimen image. The outlining algorithm can be applied to either a binary or grayscale form of the specimen image by selecting the appropriate Binary or Grayscale checkbox. Visitors should explore the effects of the segmentation algorithm on the appearance of the Specimen Image and its corresponding histogram.
The segmentation algorithm (for both grayscale and binary images) operates by creating a dilated as well as an eroded copy of the original image. Dilation adds a layer of pixels to the boundaries of image features, causing these features to grow by one pixel along their boundaries. Erosion has the opposite effect of removing a layer of pixels from feature boundaries, inducing a single-pixel shrink along the borders. The eroded image is then subtracted pixel-by-pixel from the dilated image to produce an outline of the features appearing in the original image. The resulting image outline can then be used to detect and measure feature boundaries, as well as to classify the various details and textures appearing in the original image. A major advantage of the outlining algorithm is that it tends to be less susceptible (than other common edge enhancement operations) to errors resulting from the presence of noise.
In the tutorial, the Erosion Iterations and Dilation Iterations sliders control the number of iterations applied to the original image by the erosion and dilation algorithms. Generally, the effect of increasing the number of iterations is to thicken the boundaries of objects, and in most cases, the number of iterations for each algorithm should be the same. This has the benefit of closing some of the holes that may appear along feature boundaries, with the disadvantage that the boundaries of closely neighboring details may merge together to give the false appearance of a single feature.
Contributing Authors
Kenneth R. Spring - Scientific Consultant, Lusby, Maryland, 20657.
John C. Long, Matthew J. Parry-Hill, and Michael W. Davidson - National High Magnetic Field Laboratory, 1800 East Paul Dirac Dr., The Florida State University, Tallahassee, Florida, 32310.
BACK TO DIGITAL IMAGE PROCESSING TUTORIALS
Questions or comments? Send us an email.
© 1998-2025 by Michael W. Davidson and The Florida State University. All Rights Reserved. No images, graphics, scripts, or applets may be reproduced or used in any manner without permission from the copyright holders. Use of this website means you agree to all of the Legal Terms and Conditions set forth by the owners.
This website is maintained by our
Graphics & Web Programming Team
in collaboration with Optical Microscopy at the
National High Magnetic Field Laboratory.
Last modification: Tuesday, May 17, 2016 at 12:00 PM
Access Count Since March 8, 2001: 3663
Visit the websites of our partners in digital imaging education:
