Abstract | ||
---|---|---|
The extension of the standard grayscale active appearance model (AAM) techniques to color images is investigated. Prior work in this field has mainly focused on RGB color models which did not demonstrate noticeable benefits over grayscale models from the point of view of convergence accuracy. We improve on previous work by normalizing the color texture vector separately for intensity and chromaticity components. Where an appropriate color space is chosen, we demonstrate improvements in convergence accuracy as well as image synthesization quality for AAMs. Optimal results are achieved when a color space in which the image channels are strongly decorrelated is chosen. Our best results are achieved using the I1I2I3 color space, originally proposed by Ohta. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/TIP.2009.2017163 | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
Keywords | Field | DocType |
color texture vector,grayscale model,active appearance model,appropriate color space,convergence accuracy,image channel,color texture normalization,color space,prior work,previous work,image synthesization quality,rgb color model,color,active appearance models,algorithms,concatenated codes,color model,gray scale,pca,convergence,image analysis,image texture,biomedical imaging,merging,color spaces,principal component analysis,decorrelation,color image | Computer vision,Color space,Pattern recognition,Color histogram,RGB color space,Color balance,RGB color model,Artificial intelligence,Color normalization,Mathematics,Color quantization,Color image | Journal |
Volume | Issue | ISSN |
18 | 6 | 1057-7149 |
Citations | PageRank | References |
5 | 0.52 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mircea C. Ionita | 1 | 211 | 9.90 |
P. M. Corcoran | 2 | 414 | 82.56 |
Vasile Buzuloiu | 3 | 345 | 28.09 |