Name
Abstract | ||
|---|---|---|
In real world, a scene is composed by many characteristics Intrinsic images represent these characteristics by two components, reflectance (the albedo of each point) and shading (the illumination of each point) Because reflectance images are invariant under different illumination conditions, they are more appropriate for some vision applications, such as recognition, detection We develop the system to separate them from a single image Firstly, a presented method, called Weighted-Map Method, is used to separate reflectance and shading A weighted map is created by first transforming original color domain into new color domain and then extracting some useful property Secondly, we build Markov Random Fields and use Belief Propagation to propagate local information in order to help us correct misclassifications from neighbors According to our experimental results, our system can apply to not only real images but also synthesized images. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-12297-2_9 | ACCV (3) |
Keywords | Field | DocType |
markov random fields,reflectance image,different illumination condition,real image,real world,new color domain,separate reflectance,original color domain,weighted map,belief propagation,single image,shading separation,characteristics intrinsic image,shading,reflectance | Computer vision,Random field,Pattern recognition,Computer science,Markov chain,Albedo,Artificial intelligence,Invariant (mathematics),Real image,Reflectivity,Shading,Belief propagation | Conference |
Volume | ISSN | ISBN |
5996 | 0302-9743 | 3-642-12296-5 |
Citations | PageRank | References |
1 | 0.38 | 9 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sung-Hsien Hsieh | 1 | 48 | 13.71 |
| Chih-Wei Fang | 2 | 26 | 2.47 |
| Te-Hsun Wang | 3 | 26 | 2.35 |
| Chien-Hung Chu | 4 | 1 | 0.72 |
| Jenn-Jier James Lien | 5 | 143 | 14.42 |