Sample selection with SOMP for robust basis recovery in sparse coding dictionary learning

Simple item page
dc.contributor.authorChatterjee, Ayan
dc.contributor.authorYuen, Peter W. T.
dc.date.accessioned2019-09-19T10:57:57Z
dc.date.available2019-09-19T10:57:57Z
dc.date.issued2019-09-03
dc.description.abstractSparse Coding Dictionary (SCD) learning is to decompose a given hyperspectral image into a linear combination of a few bases. In a natural scene, because there is an imbalance in the abundance of materials, the problem of learning a given material well is directly proportional to its abundance in the training scene. By a random selection of pixels to train a given dictionary, the probability of bases learning a given material is proportional to its distribution in the scene. We propose to use SOMP residue for sample selection with each iteration for a more robust or ‘more complete’ learning. Experiments show that the proposed method learns from both background and trace materials accurately with over 0.95 in Pearson correlation coefficient. Furthermore, the proposed implementation has resulted in considerable improvements in Target Detection with Adaptive Cosine Estimator (ACE).en_UK
dc.identifier.citationChatterjee A and Yuen PWT. Sample selection with SOMP for robust basis recovery in sparse coding dictionary learning. IEEE Letters of the Computer Society, Volume 2, Issue 3, 2019, pp. 28-31en_UK
dc.identifier.issn2573-9689
dc.identifier.urihttps://doi.org/10.1109/LOCS.2019.2938446
dc.identifier.urihttp://dspace.lib.cranfield.ac.uk/handle/1826/14544
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectHyperspectral imagingen_UK
dc.subjectsparse codingen_UK
dc.subjectDictionary learningen_UK
dc.titleSample selection with SOMP for robust basis recovery in sparse coding dictionary learningen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Sample_selection_with_SOMP_for_robust_basis_recovery-2019.pdf
Size:
675.7 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (CDS)