|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
| | ||
| Search | ||
| ||
Spatially Varying Color Distributions for Interactive Multilabel Segmentation
May 2013 (vol. 35 no. 5)
pp. 1234-1247
| ASCII Text | x | ||
| Claudia Nieuwenhuis, Daniel Cremers, "Spatially Varying Color Distributions for Interactive Multilabel Segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 5, pp. 1234-1247, May, 2013. | |||
| BibTex | x | ||
| @article{ 10.1109/TPAMI.2012.183, author = {Claudia Nieuwenhuis and Daniel Cremers}, title = {Spatially Varying Color Distributions for Interactive Multilabel Segmentation}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {35}, number = {5}, issn = {0162-8828}, year = {2013}, pages = {1234-1247}, doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2012.183}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - JOUR JO - IEEE Transactions on Pattern Analysis and Machine Intelligence TI - Spatially Varying Color Distributions for Interactive Multilabel Segmentation IS - 5 SN - 0162-8828 SP1234 EP1247 EPD - 1234-1247 A1 - Claudia Nieuwenhuis, A1 - Daniel Cremers, PY - 2013 KW - Image color analysis KW - Image segmentation KW - Joints KW - Motion segmentation KW - Kernel KW - Probability distribution KW - Bayesian methods KW - convex optimization KW - Image segmentation KW - spatially varying KW - color distribution VL - 35 JA - IEEE Transactions on Pattern Analysis and Machine Intelligence ER - | |||
We propose a method for interactive multilabel segmentation which explicitly takes into account the spatial variation of color distributions. To this end, we estimate a joint distribution over color and spatial location using a generalized Parzen density estimator applied to each user scribble. In this way, we obtain a likelihood for observing certain color values at a spatial coordinate. This likelihood is then incorporated in a Bayesian MAP estimation approach to multiregion segmentation which in turn is optimized using recently developed convex relaxation techniques. These guarantee global optimality for the two-region case (foreground/background) and solutions of bounded optimality for the multiregion case. We show results on the GrabCut benchmark, the recently published Graz benchmark, and on the Berkeley segmentation database which exceed previous approaches such as GrabCut [32], the Random Walker [15], Santner's approach [35], TV-Seg [39], and interactive graph cuts [4] in accuracy. Our results demonstrate that taking into account the spatial variation of color models leads to drastic improvements for interactive image segmentation.
Index Terms:
Image color analysis,Image segmentation,Joints,Motion segmentation,Kernel,Probability distribution,Bayesian methods,convex optimization,Image segmentation,spatially varying,color distribution
Citation:
Claudia Nieuwenhuis, Daniel Cremers, "Spatially Varying Color Distributions for Interactive Multilabel Segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 5, pp. 1234-1247, May 2013, doi:10.1109/TPAMI.2012.183
Usage of this product signifies your acceptance of the Terms of Use.

