Haritopoulos, Michel, Yin, Hujun and Allinson, Nigel (2001) Multiplicative noise removal using self-organizing maps. In: Independent Component Analysis, 9-12 December 2001.
Full content URL: http://inc2.ucsd.edu/ica2001/un1.html
| Documents |
| ||||
![[img]](http://eprints.lincoln.ac.uk/style/images/fileicons/application_pdf.png) |
PDF
022-haritopoulos.pdf - Whole Document Restricted to Repository staff only 510kB |
| Item Type: | Conference or Workshop contribution (Paper) |
|---|---|
| Item Status: | Live Archive |
Abstract
This paper approaches the problem of image denoising from an Independent Component Analysis (ICA) perspective. Considering that the pixels intensity constituting the crude images represents the useful signal corrupted with noise, we show that, a nonlinear ICA-based approach can provide a satisfactory solution to the Non-Linear Blind Source Separation problem (NLBSS). Self-Organizing Maps (SOMs) are well suited for performing this task, due to their nonlinear mapping property. Separation results obtained from test images demonstrate the feasibility of the proposed method.
| Additional Information: | This paper approaches the problem of image denoising from an Independent Component Analysis (ICA) perspective. Considering that the pixels intensity constituting the crude images represents the useful signal corrupted with noise, we show that, a nonlinear ICA-based approach can provide a satisfactory solution to the Non-Linear Blind Source Separation problem (NLBSS). Self-Organizing Maps (SOMs) are well suited for performing this task, due to their nonlinear mapping property. Separation results obtained from test images demonstrate the feasibility of the proposed method. |
|---|---|
| Keywords: | Multiplicative Noise, Removal Using Self, Organizing Maps |
| Subjects: | G Mathematical and Computer Sciences > G400 Computer Science |
| Divisions: | College of Science > School of Computer Science |
| ID Code: | 5023 |
| Deposited On: | 20 Apr 2012 09:05 |
Repository Staff Only: item control page