Robust Segmentation of Relevant Regions in Low Depth of Field Images
by Franz Graf, Hans-Peter Kriegel, Michael Weiler
Published at IEEE International Conference on Image Processing 2011 (ICIP)
Conference Date: Sep 11, 2011 - Sep 14, 2011
Conference Location: Brussels, Belguim.
Abstract:
Low depth of field (DOF) is an important technique to emphasize the object of interest (OOI) within an image. When viewing a low depth of field image, the viewer implicitly segments the image into region of interest and non regions of interest which has major impact on the perception of the image. Thus, robust algorithms for the detection of the OOI in low DOF images provide valuable information for subsequent image processing and image retrieval. In this paper we propose a robust and parameterless algorithm for the fully automatic segmentation of low depth of field images. We compare our method with three similar methods and show the superior robustness even though our algorithm does not require any parameters to be set by hand. The experiments are conducted on a real world data set with high and low depth of field images.
Copyright
Please refer to IEEE Xplore for obtaining copyrights!
Documents:
- Paper
- Poster
- Online Demo Site / Launch direktly (Requires Java 6, get it here.)
- Test Data 63 HighRes test images including masks (~75Mb)
- Full Source Code as zipped NetBeans project.
The Source Code includes the algorithm as well as the comparison partners mentioned in the paper. You can just unpack it and open it as a NetBeans project. If you do not use NetBeans, you might run into a missing Library which is not included in the ZIP.
Please do not send emails asking for support about the code as we do not have the ressources to provide according support.
Bibtex
@INPROCEEDINGS{GraKriWei11,
AUTHOR = "Franz Graf and Hans-Peter Kriegel and Michael Weiler",
TITLE = "Robust Segmentation of Relevant Regions in Low Depth of Field Images",
BOOKTITLE = "2011 IEEE International Conference on Image Processing (IEEE ICIP2011)",
ADDRESS = "Brussels, Belgium",
DAYS = 11,
MONTH = 9,
YEAR = 2011,
KEYWORDS = "Image Segmentation, Low Depth of Field, Object of Interest"
}
Errata
Reference [10] should honor
Segmenting a Low-Depth-of-Field Image Using Morphological Filters and Region Merging.
C. Kim, IEEE Transactions on Image Processing 14(10):1503-1511 (2005)
Source:
dx.doi.org,
IEEE Xplore,
Author's home
As it is literaly the same work, just 2 years before.
