An image-processing system has been developed for a Macintosh II personal computer. It is designed to process individual sagittal tongue sections that are digitized in real time and stored in standard TIFF format. The successive processing steps are: (1) a prefilter for noise reduction, (2) a geometrical transformation (polar coordinates), (3) an enhancement of the tissue/air interface in the surface region of the tongue by matched filtering, and (4) an extraction of border points by searching for an optimal radial path along the angular dimension. This latter task is performed very efficiently using dynamic programming, which has several advantages. First, the procedure is very robust, due to the use of a global criterion to guide the detection. Second, the extracted contours are smooth as a result of appropriate restriction of the allowable transitions. Finally, the method allows an optional specification of some predefined contour points. This system was implemented into a program that can handle image sequences in a fully automatic mode.

Agency
National Institute of Health (NIH)
Institute
National Center for Research Resources (NCRR)
Type
Intramural Research (Z01)
Project #
1Z01RR010344-02
Application #
3874208
Study Section
Project Start
Project End
Budget Start
Budget End
Support Year
2
Fiscal Year
1991
Total Cost
Indirect Cost
Name
National Center for Research Resources
Department
Type
DUNS #
City
State
Country
United States
Zip Code