Ivica Kopriva, Senior Scientist, Rudjer Boskovic Institute, Zagreb, Croatia
Title:Nonlinear sparse component analysis: low-contrast multichannel image decomposition
Abstract:
Blind (unsupervised) signal separation (BSS) is one of the fundamental problems in signal/information processing. Thereby,
underdetermined nonlinear blind separation of correlated signals is especially challenging. Solution of nonlinear BSS problem
is of practical importance, among others, in decomposition (segmentation) of multichannel image composed of objects with
highly similar spectra or densities. We shall present method for nonlinear BSS problem in Hilbert kernel spaces (Kopriva et
al, J. Chemometrics 28, 704-715, 2014; J. Chemometrics 27, 189-197, 2013). The method will be demonstrated on segmentation
of RGB microscopic images of unstained specimens in histopathology (Kopriva et al, Scientific Reports 5: 11576,
DOI: 10.1038/srep11576).
Brief Bio:
Ivica Kopriva obtained PhD degree from the Faculty of Electrical Engineering and Computing, University of Zagreb in 1998 with a
subject in blind source separation. From 2001 till 2005 he was research and senior research scientist at Department of Electrical
and Computer Engineering, The George Washington University, Washington D.C., USA. Since 2006 he is senior scientist at the
Ruđer Bošković Institute, Zagreb, Croatia. His research interests are related to development of algorithms for unsupervised learning
with applications in biomedical image analysis, chemometrics and bioinformatics. He published over 40 papers in internationally
recognized journals and hold 3 US patents. He is co-author of the research monograph: Kernel Based Algorithms for Mining Huge
Data Sets: Supervised, Semi-supervised and Unsupervised Learning, Springer Series: Studies in Computational Intelligence, 2006.
He is senior member of the IEEE and the OSA.