Title :
Picture blind source separation by auto-encoder identity mapping with structural pruning
Author :
Yasui, S. ; Takahashi, S. ; Furukawa, T.
Author_Institution :
Graduate Sch. of Life Sci. & Syst. Eng., Kyushu Inst. of Technol., Kitakyushu, Japan
Abstract :
A non-information-theoretic approach applied here for BSS of image data (pictures) is based on an auto-encoder neural network that incorporates a pruning algorithm. Nonlinear hidden units that survive the pruning will be the source extractors. The BSS state is attained as a local minimum of the error associated with the identity mapping by the auto-encoder. An internal mixing model is automatically induced in the decoder part. The BSS performance is shown to be satisfactory, including trouble cases involving noise or blanks in the mixed pictures.
Keywords :
blind source separation; image coding; learning (artificial intelligence); neural nets; auto-encoder neural network; image coding; image data; internal mixing model; learning; picture blind source separation; pruning algorithm; structural pruning; Blind source separation; Data compression; Data engineering; Data mining; Decoding; Neural networks; Principal component analysis; Source separation; Symmetric matrices; Systems engineering and theory;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1202849