000171857 001__ 171857
000171857 005__ 20180913060950.0
000171857 02470 $$2ISI$$a000294955300051
000171857 037__ $$aCONF
000171857 245__ $$aFast Ray Features for Learning Irregular Shapes
000171857 269__ $$a2009
000171857 260__ $$bIeee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa$$c2009
000171857 336__ $$aConference Papers
000171857 490__ $$aIEEE International Conference on Computer Vision
000171857 520__ $$aWe introduce a new class of image features, the Ray feature set, that consider image characteristics at distant contour points, capturing information which is difficult to represent with standard feature sets. This property allows Ray features to efficiently and robustly recognize deformable or irregular shapes, such as cells in microscopic imagery. Experiments show Ray features clearly outperform other powerful features including Haar-like features and Histograms of Oriented Gradients when applied to detecting irregularly shaped neuron nuclei and mitochondria. Ray features can also provide important complementary information to Haar features for other tasks such as face detection, reducing the number of weak learners and computational cost.
000171857 6531_ $$aMedical Imagery, Face Detection, Image Features
000171857 700__ $$0242712$$aSmith, Kevin$$g163328
000171857 700__ $$0240253$$aCarleton, Alan$$g163091
000171857 700__ $$0240235$$aLepetit, Vincent$$g149007
000171857 7112_ $$a12th IEEE International Conference on Computer Vision$$cKyoto, JAPAN$$dSep 29-Oct 02, 2009
000171857 773__ $$q397-404$$t2009 IEEE 12Th International Conference On Computer Vision (ICCV)
000171857 8564_ $$s3692119$$uhttps://infoscience.epfl.ch/record/171857/files/smith_iccv09.pdf$$yPostprint$$zPostprint
000171857 909C0 $$0252087$$pCVLAB$$xU10659
000171857 909CO $$ooai:infoscience.tind.io:171857$$pconf$$pIC
000171857 917Z8 $$x149007
000171857 937__ $$aEPFL-CONF-171857
000171857 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000171857 980__ $$aCONF