DocumentCode
384127
Title
Ranklets: orientation selective non-parametric features applied to face detection
Author
Smeraldi, Fabrizio
Author_Institution
Halmstad Univ., Sweden
Volume
3
fYear
2002
fDate
2002
Firstpage
379
Abstract
We introduce a family of multiscale, orientation-selective, non-parametric features ("ranklets") modelled on Haar wavelets. We clarify their relation to the Wilcoxon rank-sum test and the rank transform and provide an efficient scheme for computation based on the Mann-Whitney statistics. Finally, we show that ranklets outperform other rank features, Haar wavelets, SNoW and linear SVMs (based on independently published results) in face detection experiments over the 24\´045 test images in the MIT-CBCL database.
Keywords
Haar transforms; face recognition; object detection; visual databases; wavelet transforms; Haar wavelets; MIT-CBCL database; Mann-Whitney statistics; Wilcoxon rank-sum test; experiments; face detection; image database; linear SVM; orientation selective nonparametric features; rank transform; ranklets; Brightness; Classification algorithms; Face detection; Image databases; Snow; Spatial databases; Statistics; Support vector machine classification; Support vector machines; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2002. Proceedings. 16th International Conference on
ISSN
1051-4651
Print_ISBN
0-7695-1695-X
Type
conf
DOI
10.1109/ICPR.2002.1047924
Filename
1047924
Link To Document