16504 search results - page 2963 / 3301 » New Problems, New Solutions |
190
click to vote
ICIP
2010
IEEE
15 years 4 months ago
2010
IEEE
When comparing 2D shapes, a key issue is their normalization. Translation and scale are easily taken care of by removing the mean and normalizing the energy. However, defining and...
172
click to vote
ICPR
2010
IEEE
15 years 4 months ago
2010
IEEE
3D face recognition exploits shape information as well as texture information in 2D systems. The use of whole 3D face is sensitive to some undesired situations like expression var...
171
click to vote
ICPR
2010
IEEE
15 years 4 months ago
2010
IEEE
We report performance evaluation of our automatic feature discovery method on the publicly available Gisette dataset: a set of 29 features discovered by our method ranks 129 among...
176
click to vote
IGARSS
2010
15 years 4 months ago
2010
Spectral unmixing is an important task for remotely sensed hyperspectral data exploitation. Linear spectral unmixing relies on two main steps: 1) identification of pure spectral c...
200
click to vote
IPPS
2010
IEEE
15 years 4 months ago
2010
IEEE
Many large-scale clusters now have hundreds of thousands of processors, and processor counts will be over one million within a few years. Computational scientists must scale their ...