The thesis discusses the possibilities of using contour shape classification for detection of mis-segmented bones in computed tomography (CT) data. In the first part there are presented published methods and algorithms which deal with the segmentation of bone structures in CT data. Then segmentation of cortical bones is implemented by a simple thresholding with global threshold. The threshold is determined by the optimized fitting of a selected type probability distribution to the histogram. Subsequently, the thesis describes some important shape descriptors that can quantitatively describe the shapes of objects in the image. Further, the contour extraction is implemented and a suitable shape descriptor, cumulative angular function, is applied. Finally, the points which can potentially indicate mis-segmented bones are detected by using continuous wavelet transform. The proposed technique is tested on the real CT data.
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:220852 |
| Date | January 2014 |
| Creators | Janovič, Tomáš |
| Contributors | Jan, Jiří, Walek, Petr |
| Publisher | Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií |
| Source Sets | Czech ETDs |
| Language | Czech |
| Detected Language | English |
| Type | info:eu-repo/semantics/masterThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0022 seconds