Illumination-robust Pattern Matching Using Distorted Color Histograms
| Type of publication: | Conference paper |
| Citation: | Thimm-98.5 |
| Booktitle: | Pattern Recognition and Image Understanding |
| Year: | 1999 |
| Publisher: | Infix |
| Address: | Sankt Augustin |
| Crossref: | thimm-98.3: |
| Abstract: | It is argued that global illumination should be modeled separately from other incidents that change the appearance of objects. The effects of intensity variations of the global illumination are discussed and constraints deduced that restrict the shape of a function that maps the histogram of a template to the histogram of an image location. This approach is illustrated for simple pattern matching and for a combination with a PCA (\emph{Eigenface}) model of the grey-level appearance. |
| Userfields: | ipdmembership={vision}, nofpages={8}, |
| Keywords: | appearance, Eigenface model, histogram, illumination variation, pattern matching |
| Projects |
Idiap |
| Authors | |
| Editors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|