An Effective Local Invariant Descriptor Combining Luminance and Color Information

Dong Zhang, Weiqiang Wang, Wen Gao, Shuqiang Jiang

Abstract

Extraction ofstable local invariant features isveryimportant inmanycomputer vision applications, suchasimage matching, object recognition andimageretrieval. Most existing localinvariant features mainlycharacterize luminance information, andneglect color information. In thispaper, we present a newlocal invariant descriptor characterizing bothofthem,whichcombines three photometric invariant color descriptors withthefamous SIFTdescriptor. Toreduce thedimension ofthecombined high-dimensional invariant feature theprincipal component analysis (PCA)isused. Ourexperiments showtheproposed local descriptor through combining luminance andcolor information outperforms thedescriptors that onlyutilize a single category ofinformation, andcombining thethree color feature representations ismoreeffective thanonly one.
BibTeX
@inproceedings{zhang2007effective,
  author = {Dong Zhang and Weiqiang Wang and Wen Gao and Shuqiang Jiang},
  title = {{An Effective Local Invariant Descriptor Combining Luminance and Color Information}},
  booktitle = {ICME},
  year = {2007},
  doi = {10.1109/icme.2007.4284948},
}

Loading related content...

Figure