SELECTION OF RECOGNITION OBJECTS’ OUTER CONTOURS ON MULTICHANNEL IMAGES
Methods for detecting contour points of objects on segmented images formed by the method of statistical recognition of multichannel data are proposed. Algorithms for linking of adjacent isolated points of the contour of the selected area using distance criteria have been developed. The obtained arra...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
National Aerospace University «Kharkiv Aviation Institute»
2017-02-01
|
| Series: | Радіоелектронні і комп'ютерні системи |
| Subjects: | |
| Online Access: | http://nti.khai.edu/ojs/index.php/reks/article/view/579 |
| Summary: | Methods for detecting contour points of objects on segmented images formed by the method of statistical recognition of multichannel data are proposed. Algorithms for linking of adjacent isolated points of the contour of the selected area using distance criteria have been developed. The obtained arrays of points belonging to the outer contour allow us to represent the boundary in the form of scans along the axes in the inertial coordinate system placed at the center of gravity of the object’s image. The algorithms approbation results confirming their effectiveness in problems of constructing brightness-geometric models of recognition objects are presented. |
|---|---|
| ISSN: | 1814-4225 2663-2012 |