Using active models for finding landmarks

• Autorzy: Kowalski P. , Tomaka A.
• Języki publikacji: EN

Abstrakty

EN

The paper presents the results of the experiments in using the active appearance models (AAM) to finding landmarks in the x-ray images of skull (especially of mandible). The landmark pointing is time-consuming in orthodontic analysis. It is useful to initially point the landmarks automatically, to help a physician in his or her work. Because the landmark are pointed not only by local features, but also by geometrical structure of skull, the model have to represent not only the local features (pixels in the image), but also the geometrical constraints. The one of many possible approaches is the active appearance model. The active appearance model was developed from the active shape models, and consists of the model of the shape and the model of appearance (texture). The model is active, that means the model fits to the object in the image. The main principle of the active models is to use two energies - internal energy represents limits of the models (shape, contour, texture), and the external energy represents the fitting the model to the image.

Słowa kluczowe

EN

active appearance models; landmarks; X-ray images; skull; mandible

PL

wygląd aktywnych modeli; punkty orientacyjne; zdjęcia rentgenowskie; czaszka; żuchwa

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2005
• Tom: Vol. 9
• Strony: 225--231
• Opis fizyczny: Bibliogr. 7 poz., rys., tab.

Twórcy

autor

Kowalski P.

• The Institute of Theoretical and Applied Informatics PAS, ul. Bałtycka 5, 44-100 Gliwice

autor

Tomaka A.

• The Institute of Theoretical and Applied Informatics PAS, ul. Bałtycka 5, 44-100 Gliwice

Bibliografia

• [1] BHATIA S.N., LEIGHTON B.C., A Manual of Facial Growth, Oxford University Press, 1993
• [2] COOTES T.F., EDWARDS G.J., TAYLOR C.J., Active Appearance Models. Proc. European Conference on Computer Vision 1998, vol. 2, pp. 484-498, Springer, 1998.
• [3] EL-FEGHI I., SID_AHMED M.A., AHMADI M., Automatic localization of craniofacial landmarks for assisted cephalometry, Pattern Recognition 37 (2004, pp. 609-621
• [4] LIU J-K., CHEN Y-T., CHENG K-S., Accuracy of computerized automatic identyfication of cephalometric landmarks, American Journal of Orthodontics and Dentofacial Orthopedics, November 2000, pp. 535-540
• [5] MATTHEWS I., BAKER S., Active Appearance Models Revisited. Tech. report CMU-RI-TR-03-02, Robotics Institute, Carnegie Mellon University, April, 2003
• [6] MCCLURE S.R., SADOWSKY P.L., FERREIRA A., JACOBSON A., Reliability of Digital Versus Conventional Cephalometric Radiology: A Comparative Evaluation of Landmark Identyfication Error, Seminars in Orthodontics, pp. 98-110, Elsevier, 2005
• [7] TOMAKA A., Detekcja i opis deformacji struktur na podstawie sekwencji obrazów cyfrowych. PhD Thesis, Gliwice, 2001