ORTHOGONAL NONNEGATIVE TUCKER DECOMPOSITION
Related Research Unit(s)
|Journal / Publication||SIAM Journal on Scientific Computing|
|Online published||7 Jan 2021|
|Publication status||Published - 2021|
|Link to Scopus||https://www.scopus.com/record/display.uri?eid=2-s2.0-85102809410&origin=recordpage|
In this paper, we study nonnegative tensor data and propose an orthogonal nonnegative Tucker decomposition (ONTD). We discuss some properties of ONTD and develop a convex relaxation algorithm of the augmented Lagrangian function to solve the optimization problem. The convergence of the algorithm is given. We employ ONTD on the image data sets from the real world applications including face recognition, image representation, and hyperspectral unmixing. Numerical results are shown to illustrate the effectiveness of the proposed algorithm.
- Image processing, Nonnegative tensor, Tucker decomposition
SIAM Journal on Scientific Computing, Vol. 43, No. 1, 2021, p. B55-B81.
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review