%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/09.08.14.26
%2 sid.inpe.br/sibgrapi/2017/09.08.14.26.44
%T Detection of 3D salient points in magnetic resonance images using the dual-tree complex wavelet transform
%D 2017
%A Zafalon Kovacs, Nicole,
%A Ferrari, Ricardo José,
%@affiliation Universidade Federal de São Carlos,
%@affiliation Universidade Federal de São Carlos,
%E Torchelsen, Rafael Piccin,
%E Nascimento, Erickson Rangel do,
%E Panozzo, Daniele,
%E Liu, Zicheng,
%E Farias, Mylène,
%E Viera, Thales,
%E Sacht, Leonardo,
%E Ferreira, Nivan,
%E Comba, João Luiz Dihl,
%E Hirata, Nina,
%E Schiavon Porto, Marcelo,
%E Vital, Creto,
%E Pagot, Christian Azambuja,
%E Petronetto, Fabiano,
%E Clua, Esteban,
%E Cardeal, Flávio,
%B Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)
%C Niterói, RJ, Brazil
%8 17-20 Oct. 2017
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K 3D salient points, DT-CWT, MRI, complex wavelets.
%X Detection of 3D salient points in medical images has many important applications such as image registration and mesh positioning for the purpose of segmentation of important anatomical structures. In this study, we present preliminary results of a proposed method for the detection of 3D salient points in Magnetic Resonance (MR) images of human brain. Our method, which is based on the Dual-Tree Complex Wavelet Transform, combines the oriented wavelet sub-bands (by multiplying the ones on the same scale and upsampling the result to an upper level scale) to create an image map in which local maxima correspond to the salient points. Qualitative assessment was conducted using 566 brain MRI images, whose results were combined together to create a point cloud showing the concentration of the salient points on important brain regions. The results indicate that our method has a great potential to detect important 3D salient points in MR images.
%@language en
%3 artigo.pdf