Title :
Nonnegative Tensor Decomposition and It´s Applications in Image Processing
Author :
Yang, Hongli ; He, Guoping ; Dong, Yulin
Author_Institution :
Inf. Sci. & Eng. Coll., Shandong Univ. of Sci. & Technol., Qingdao
fDate :
Aug. 29 2008-Sept. 2 2008
Abstract :
Nonnegative tensor decomposition is an effective data processing technique that has proven to be useful for a wide variety of applications. In this paper we get some results that a three order tensor can be represented by the matrix product. By the representation of matrix product, we give an iterative algorithm for nonnegative tensor decomposition which has good performance. We also applied our algorithm to image processing, and the reconstruct image is in good quality.
Keywords :
image reconstruction; iterative methods; matrix decomposition; tensors; data processing technique; image processing; image quality; image reconstruction; iterative algorithm; matrix product representation; nonnegative tensor decomposition; Algebra; Application software; Computer science; Helium; Image processing; Information technology; Iterative algorithms; Matrix decomposition; Signal processing algorithms; Tensile stress; algorithm; image processing; nonnegative tensor decomposition;
Conference_Titel :
Computer Science and Information Technology, 2008. ICCSIT '08. International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-0-7695-3308-7
DOI :
10.1109/ICCSIT.2008.99