Name
Abstract | ||
|---|---|---|
This paper addresses the problem of recognizing shadows from monochromatic natural images. Without chromatic information, shadow classification is very challenging because the invariant color cues are unavailable. Natural scenes make this problem even harder because of ambiguity from many near black objects. We propose to use both shadow-variant and shadow-invariant cues from illumination, textural and odd order derivative characteristics. Such features are used to train a classifier from boosting a decision tree and integrated into a Conditional random Field, which can enforce local consistency over pixel labels. The proposed approach is evaluated using both qualitative and quantitative results based on a novel database of hand-labeled shadows. Our results show shadowed areas of an image can be identified using proposed monochromatic cues. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/CVPR.2010.5540209 | CVPR |
Keywords | Field | DocType |
shadow classification,random processes,shadow-variant cues,shadow recognition,image classification,conditional random field,object recognition,natural scenes,monochromatic natural image,image texture,illumination,decision tree,decision trees,shadow-invariant cues,entropy,lighting,image segmentation,image recognition,histograms,labeling,layout,computer science,pixel,databases,image sensors | Conditional random field,Shadow,Computer vision,Monochromatic color,Pattern recognition,Image texture,Computer science,Image segmentation,Boosting (machine learning),Artificial intelligence,Pixel,Contextual image classification | Conference |
Volume | Issue | ISSN |
2010 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
978-1-4244-6984-0 | 51 | 1.83 |
References | Authors | |
26 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jiejie Zhu | 1 | 378 | 21.71 |
| Kegan G. G. Samuel | 2 | 87 | 3.26 |
| Syed Z. Masood | 3 | 61 | 2.55 |
| Marshall F. Tappen | 4 | 1901 | 89.34 |