Spectral Grouping Using the Nyström Method
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Spectral Grouping Using the Nyström Method. / Fowlkes, Charless; Belongie, Serge; Chung, Fan; Malik, Jitendra.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 2, 02.2004, p. 214-225.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Spectral Grouping Using the Nyström Method
AU - Fowlkes, Charless
AU - Belongie, Serge
AU - Chung, Fan
AU - Malik, Jitendra
PY - 2004/2
Y1 - 2004/2
N2 - Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation. However, due to the computational demands of these approaches, applications to large problems such as spatiotemporal data and high resolution imagery have been slow to appear. The contribution of this paper is a method that substantially reduces the computational requirements of grouping algorithms based on spectral partitioning making it feasible to apply them to very large grouping problems. Our approach is based on a technique for the numerical solution of eigenfunction problems known as the Nyström method. This method allows one to extrapolate the complete grouping solution using only a small number of samples. In doing so, we leverage the fact that there are far fewer coherent groups in a scene than pixels.
AB - Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation. However, due to the computational demands of these approaches, applications to large problems such as spatiotemporal data and high resolution imagery have been slow to appear. The contribution of this paper is a method that substantially reduces the computational requirements of grouping algorithms based on spectral partitioning making it feasible to apply them to very large grouping problems. Our approach is based on a technique for the numerical solution of eigenfunction problems known as the Nyström method. This method allows one to extrapolate the complete grouping solution using only a small number of samples. In doing so, we leverage the fact that there are far fewer coherent groups in a scene than pixels.
KW - Clustering
KW - Image and video segmentation
KW - Normalized cuts
KW - Nyström approximation
KW - Spectral graph theory
UR - http://www.scopus.com/inward/record.url?scp=0742286179&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2004.1262185
DO - 10.1109/TPAMI.2004.1262185
M3 - Journal article
C2 - 15376896
AN - SCOPUS:0742286179
VL - 26
SP - 214
EP - 225
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 2
ER -
ID: 302055737