Microscopy Primer
Light and Color
Microscope Basics
Special Techniques
Digital Imaging
Confocal Microscopy
Live-Cell Imaging
Photomicrography
Microscopy Museum
Virtual Microscopy
Fluorescence
Web Resources
License Info
Image Use
Custom Photos
Partners
Site Info
Contact Us
Publications
Home

The Galleries:

Photo Gallery
Silicon Zoo
Pharmaceuticals
Chip Shots
Phytochemicals
DNA Gallery
Microscapes
Vitamins
Amino Acids
Birthstones
Religion Collection
Pesticides
BeerShots
Cocktail Collection
Screen Savers
Win Wallpaper
Mac Wallpaper
Movie Gallery

Automatic Threshold Level Selection

Producing binary images by means of manual selection of threshold values makes use of powerful human capabilities for recognition, but also raises problems of reproducibility, and makes automation difficult. It is also hard to communicate to someone else the rationale for selecting a particular value. Consequently, there has been considerable interest in finding algorithms that can select threshold values. Various strategies for setting thresholds automatically have been proposed, with varying degrees of success. No method works well for all images, although finding one that produces good results for a given class of pictures is often possible.

A major area of application has been to discriminate printed text on paper (as a precursor to optical character recognition and the conversion of printed pages to files suitable for word processing). This interactive tutorial illustrates several automatic thresholding algorithms for producing binary images. In the tutorial, four representative automatic methods that divide the pixels into two populations are compared:

  1. midpoint (average of the means of the two groups)
  2. statistical (maximizes the statistical difference between the groups based on the t-test)
  3. entropy (maximizes the combined entropy of the groups)
  4. probability (maximizes the probability that the pixels belong to each group)

The tutorial initializes with a randomly selected specimen imaged in the microscope appearing in the left-hand window entitled Specimen Image. The Choose A Specimen pull-down menu provides a selection of specimen images, in addition to the initial randomly chosen one. Adjacent to the Specimen Image window is the Grayscale Histogram window which displays the histogram of the brightness values in the specimen image. The Display Image buttons display in the left-hand window either the Original image, or the binary image produced by the four algorithms described: Midpoint, Statistical, Entropy or Probability. Selecting any of the latter Display Image buttons will cause a superimposed red line representing the threshold level setting to appear in the Grayscale Histogram window. The corresponding threshold level is then illustrated in text below the Grayscale Histogram window.

Contributing Authors

John C. Russ - Materials Science and Engineering Dept., North Carolina State University, Raleigh, North Carolina, 27695.

Matthew 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 INTRODUCTION TO DIGITAL IMAGE PROCESSING AND ANALYSIS

BACK TO MICROSCOPY PRIMER HOME

Questions or comments? Send us an email.
© 1998-2009 by Michael W. Davidson, John Russ, Olympus America Inc., 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, Sep 11, 2018 at 02:18 PM
Access Count Since July 20, 2006: 5562
For more information on microscope manufacturers,
use the buttons below to navigate to their websites: