Toward a robust system to monitor the head motions during PET based on facial landmarks detection: a new approach.
Gao, Xiaohong W. and Podladchikova, L. N. and Shaposhnikov, D. G. and Comley, Richard A. and Anishenko, Sergey and Osimov, Vladislav (2008) Toward a robust system to monitor the head motions during PET based on facial landmarks detection: a new approach. In: Proceedings of the 21st IEEE international symposium on computer-based medical systems. Puuronen, Seppo, ed. IEEE Computer Society, Jyväskylä, Finland.
Full text is not in this repository.
Official URL: http://www.computer.org/portal/web/csdl/doi/10.110...
A new approach for the detection of head motions during PET scanning is presented. The proposed system includes 4 modules, which are: input module, face segmentation, facial landmark detection, and head movement estimation. The developed system is tested on pictures monitoring a subject's head while simulating PET scanning (n=12) and face images of subjects with different skin colours (n=31). Experimental results show that the centres of chosen facial landmarks (eye corners and middle point of nose basement) can be detected with high precision (1?0.64 pixels). Processing of 2D images with known moving parameters demonstrates that the parameter movement in terms of rotation and translation along X, Y, and Z directions can be obtained very accurately via the developed methods.
|Item Type:||Book Section|
Conference held on June 17-19, 2008, at Jyvaskyla, Finland.
|Research Areas:||A. Middlesex University Schools and Centres > School of Science and Technology > Computer Science > Artificial Intelligence group|
A. Middlesex University Schools and Centres > School of Science and Technology > Computer Science
A. Middlesex University Schools and Centres > School of Science and Technology > Computer and Communications Engineering
|Deposited On:||01 Apr 2009 14:14|
|Last Modified:||30 Jan 2015 16:20|
Repository staff only: item control page
Full text downloads (NB count will be zero if no full text documents are attached to the record)
Downloads per month over the past year