Spectral Matting

Spectral Matting

We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence 2008-10, Vol.30 (10), p.1699-1712
Hauptverfasser: Levin, A., Rav Acha, A., Lischinski, D.
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Artificial Intelligence
Fuzzy
Fuzzy logic
Fuzzy set theory
Fuzzy sets
Image analysis
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image segmentation
Imaging, Three-Dimensional - methods
Karhunen-Loeve transforms
Laplace equations
Matrix decomposition
Mattes
matting
Motion pictures
Pattern analysis
Pattern Recognition, Automated - methods
Pixel
Production
Reproducibility of Results
Segments
Sensitivity and Specificity
Signal Processing, Computer-Assisted
Spectra
Spectral analysis
Subtraction Technique
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.
ISSN:0162-8828
1939-3539
DOI:10.1109/TPAMI.2008.168