Title :
Application of mathematical morphology to the extraction of craniofacial landmarks
Author :
Cardillo, J. ; Sid-Ahmed, M.A.
Author_Institution :
Dept. of Electr. Eng., Windsor Univ., Ont., Canada
Abstract :
An algorithm has been developed to extract craniofacial landmarks from skull X-rays. The locations of these landmarks are used by orthodontists in the diagnosis of anomalies and in the monitoring of treatments. The shape recognition algorithm is based on gray-scale mathematical morphology. A statistical approach was used to overcome subtle differences in skeletal topographies. Decomposition was used to desensitize the algorithm to size differences. A method for minimizing the search windows is presented. A system was trained to locate 20 landmarks. Preliminary tests on 30 X-rays showed a 80% recognition rate
Keywords :
computerised pattern recognition; computerised picture processing; diagnostic radiography; medical diagnostic computing; anomalies diagnosis; craniofacial landmarks; decomposition; gray scale; mathematical morphology; orthodontists; recognition rate; search windows; shape recognition algorithm; skeletal topographies; skull X-rays; statistical approach; treatment monitoring; Graphics; Monitoring; Morphological operations; Robustness; Shape; Skull; Surface morphology; Surface topography; Testing; X-rays;
Conference_Titel :
Communications, Computers and Signal Processing, 1991., IEEE Pacific Rim Conference on
Conference_Location :
Victoria, BC
Print_ISBN :
0-87942-638-1
DOI :
10.1109/PACRIM.1991.160842
