TY - JOUR
T1 - Spectral matting
AU - Levin, Anat
AU - Rav-Acha, Alex
AU - Lischinski, Dani
PY - 2008
Y1 - 2008
N2 - We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.
AB - We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.
KW - Image matting
KW - Spectral analysis
KW - Unsupervised segmentation
UR - http://www.scopus.com/inward/record.url?scp=50249161297&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2008.168
DO - 10.1109/TPAMI.2008.168
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 18703825
AN - SCOPUS:50249161297
SN - 0162-8828
VL - 30
SP - 1699
EP - 1712
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 10
ER -