TY - JOUR
T1 - Full multiresolution active shape models
AU - Cerrolaza, Juan J.
AU - Villanueva, Arantxa
AU - Sukno, Federico M.
AU - Butakoff, Constantine
AU - Frangi, Alejandro F.
AU - Cabeza, Rafael
N1 - Funding Information:
Acknowledgements The work described in this study was supported by the Spanish Ministry of Science and Innovation with an FPU grant (AP2007-03931). This work was also partially supported by the Spanish Ministry of Science and Innovation (Ref. TIN2009-14536-C02-01), Plan E and FEDER.
Funding Information:
Dr. Frangi was Ramón y Cajal Research Fellow (2003–2007), a foreign member of the Review College of the Engineering and Physical Sciences Research Council (EPSRC) in UK (2006–2010), and recipient of the IEEE Engineering in Medicine and Biology Early Career Award in 2006, the Prizes for Knowledge Transfer (2008) in the Information and Communication Technologies domain, and of the Prize for Excellence (2008, 2010) by the Social Council of the Universitat Pompeu Fabra.
PY - 2012/11
Y1 - 2012/11
N2 - The incorporation of a multiresolution image approach is one of the most popular variants of Active Shape Models (ASMs), providing a more robust algorithm and minimizing its initialization dependency. Using the wavelet transform, the present paper extends the multiresolution analysis to the shape space, developing a novel multiresolution shape framework, capable of being incorporated into most of ASM variants. The tests performed with two different types of images, face images (AR database) and chest radiographs (JSRT database), demonstrate how this new generation of algorithms significantly reduce the computational cost, more than halving it, while maintaining the same levels of accuracy.
AB - The incorporation of a multiresolution image approach is one of the most popular variants of Active Shape Models (ASMs), providing a more robust algorithm and minimizing its initialization dependency. Using the wavelet transform, the present paper extends the multiresolution analysis to the shape space, developing a novel multiresolution shape framework, capable of being incorporated into most of ASM variants. The tests performed with two different types of images, face images (AR database) and chest radiographs (JSRT database), demonstrate how this new generation of algorithms significantly reduce the computational cost, more than halving it, while maintaining the same levels of accuracy.
KW - Active shape model
KW - Medical image segmentation
KW - Multiresolution analysis
KW - Wavelet transform
UR - https://link.springer.com/article/10.1007/s10851-012-0338-y
U2 - 10.1007/s10851-012-0338-y
DO - 10.1007/s10851-012-0338-y
M3 - Article
SN - 0924-9907
VL - 44
SP - 463
EP - 479
JO - Journal of Mathematical Imaging and Vision
JF - Journal of Mathematical Imaging and Vision
IS - 3
ER -