Title :
Automatic localization of craniofacial landmarks for assisted cephalometry
Author :
El-Feghi, I. ; Sid-Ahmed, M.A. ; Ahmadi, M.
Author_Institution :
Dept. of Electr. & Comput. Eng., Windsor Univ., Ont., Canada
Abstract :
In this work we propose a system for localization of cephalometric landmarks. The process of localization is carried out in two step: deriving a smaller expectation window for each landmark using a trained neuro-fuzzy system (NFS,) then applying a template-matching algorithm to pin point the exact location of the landmark. The system is trained to locate 20 landmarks on a database of 200 images. Preliminary results show an average of 90% recognition rate.
Keywords :
biomedical measurement; diagnostic radiography; fuzzy neural nets; image matching; medical image processing; pattern clustering; assisted cephalometry; automatic localization; cephalometric landmarks; craniofacial landmarks; data clustering; expectation window; head dimensions measurement; image database; lateral skull radiographs; recognition rate; template-matching algorithm; trained neuro-fuzzy system; Data mining; Diagnostic radiography; Feature extraction; Fuzzy neural networks; Head; Image analysis; Image databases; Image edge detection; Land use planning; Skull;
Conference_Titel :
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
Print_ISBN :
0-7803-7761-3
DOI :
10.1109/ISCAS.2003.1205098
