Abstract | ||
---|---|---|
We present a novel representation for modeling textured regions subject to smooth variations in orientation and scale. Utilizing the steerable pyramid of Simoncelli and Freeman as a basis, we decompose textured regions of nat- ural images into explicit local attributes of contrast, bias, scale, and orientation. Additionally, we impose smooth- ness on these attributes via Markov random fields. The combinationallowsfordemonstrableimprovementsincom- mon scene analysis applications including unsupervised segmentation, reflectance and shading estimation, and es- timation of the radiometric response function from a single image. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICCV.2009.5459317 | ICCV |
Field | DocType | Volume |
Computer vision,Random field,Pattern recognition,Computer science,Segmentation,Markov chain,Robustness (computer science),Image segmentation,Radiometry,Artificial intelligence,Pixel,Smoothness | Conference | 2009 |
Issue | ISSN | Citations |
1 | 1550-5499 | 2 |
PageRank | References | Authors |
0.38 | 13 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jason Chang | 1 | 133 | 6.75 |
John W. Fisher III | 2 | 878 | 74.44 |