hrcak mascot   Srce   HID

Izvorni znanstveni članak

The Innovations Approach to Single Frame Multichannel Blind Image Deconvolution

Ivica Kopriva ; Rudjer Boskovic Institute, Zagreb, Croatia
Damir Seršić ; Faculty of Electrical Enginering and Computing, University of Zagreb, Zagreb, Croatia

Puni tekst: engleski, pdf (1 MB) str. 345-352 preuzimanja: 423* citiraj
APA 6th Edition
Kopriva, I. i Seršić, D. (2010). The Innovations Approach to Single Frame Multichannel Blind Image Deconvolution. Automatika, 51 (4), 345-352. Preuzeto s https://hrcak.srce.hr/65057
MLA 8th Edition
Kopriva, Ivica i Damir Seršić. "The Innovations Approach to Single Frame Multichannel Blind Image Deconvolution." Automatika, vol. 51, br. 4, 2010, str. 345-352. https://hrcak.srce.hr/65057. Citirano 25.06.2019.
Chicago 17th Edition
Kopriva, Ivica i Damir Seršić. "The Innovations Approach to Single Frame Multichannel Blind Image Deconvolution." Automatika 51, br. 4 (2010): 345-352. https://hrcak.srce.hr/65057
Harvard
Kopriva, I., i Seršić, D. (2010). 'The Innovations Approach to Single Frame Multichannel Blind Image Deconvolution', Automatika, 51(4), str. 345-352. Preuzeto s: https://hrcak.srce.hr/65057 (Datum pristupa: 25.06.2019.)
Vancouver
Kopriva I, Seršić D. The Innovations Approach to Single Frame Multichannel Blind Image Deconvolution. Automatika [Internet]. 2010 [pristupljeno 25.06.2019.];51(4):345-352. Dostupno na: https://hrcak.srce.hr/65057
IEEE
I. Kopriva i D. Seršić, "The Innovations Approach to Single Frame Multichannel Blind Image Deconvolution", Automatika, vol.51, br. 4, str. 345-352, 2010. [Online]. Dostupno na: https://hrcak.srce.hr/65057. [Citirano: 25.06.2019.]

Sažetak
The linear mixture model (LMM) has recently been used for multi-channel representation of a blurred image. This enables use of multivariate data analysis methods such as independent component analysis (ICA) to solve blind image deconvolution as an instantaneous blind source separation (BSS) requiring no a priori knowledge about the size and origin of the blurring kernel. However, there remains a serious weakness of this approach: statistical dependence between hidden variables in the LMM. The contribution of this paper is an application of the ICA algorithms to the innovations of the LMM to learn the unknown basis matrix. The hidden source image is recovered by applying pseudo-inverse of the learnt basis matrix to the original LMM. The success of this approach is due to the property of the innovations of being more independent and more non-Gaussian than original processes. Our good, consistent simulation and experimental results demonstrate viability of the proposed concept.

Ključne riječi
Blind deconvolution; Image restoration; Independent component analysis; Innovations; Statistically dependent sources

Hrčak ID: 65057

URI
https://hrcak.srce.hr/65057

[hrvatski]

Posjeta: 691 *