SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
Segmentation Using Eigenvectors: A Unifying View
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Multiclass Spectral Clustering
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Efficient matching of large-size histograms
Pattern Recognition Letters
ACM SIGGRAPH 2004 Papers
Depth-of-field-based alpha-matte extraction
APGV '05 Proceedings of the 2nd symposium on Applied perception in graphics and visualization
ACM SIGGRAPH 2006 Papers
A Closed-Form Solution to Natural Image Matting
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image and video matting: a survey
Foundations and Trends® in Computer Graphics and Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Data clustering: 50 years beyond K-means
Pattern Recognition Letters
Temporally coherent video matting
Graphical Models
Automatic spectral video matting
Pattern Recognition
Hi-index | 0.00 |
Spectral matting is the state-of-the-art image matting and also a milestone in theoretic matting research. For spectral matting without user intervention, the accuracy of alpha matte is low and the computational cost is high. Therefore, this paper presents a modified version of spectral matting to greatly increase the accuracy of alpha matte and effectively reduce the computational cost. In the proposed modified spectral matting, palette-based component classification is used to obtain reliable foreground and background components. Next, the corresponding matting components are obtained via a linear transformation of the smallest eigenvectors of the matting Laplacian matrix. Finally, the matting components of the foreground and the unknown regions are combined to from the complete alpha matte based on minimizing the matte cost. Moreover, image composition with consistency of color temperature is used to obtain the realistic image composition. Experimental results show that the proposed method outperforms the state-of-the-art methods based on spectral matting.