E-mail: eduf@cccc.net.cn http://www.dnzs.net.cn Tel:+86-551-5690963 5690964 ISSN 1009-3044 ? 5 ?? 2 w ed and Te hn log ? ) Computer Kno8 l?ge (2009c? o10 y ???? ??? Vol.5,No.28, October 2009, pp.8023 ?? PCA ? LBP ????????? ??? ???? ? ???? ?????? ? ?? ?? 330031 ? ?? ? ??????? (PCA) ????????? (LBP) ? ? ? ? ? ? ? ? ? ? ? ? ? PCA ? ? ? ? ? ? ? ? ? ? ? ? ? LBP ? ????????????? ? ????????????????????? ?SVM ? ????????????? ? ???? ?? LBP ??? ? ???? LBP ?????? ? ???????????? LBP ????? ? ??????? LBP ??? PCA ? ?????? SVM ? ?????? ?LBP ? PCA ?????????? PCA ??? LBP ??????????????? ? ??? ? ?? ? ???? ? ????? ? ?????? ? ????? ????? ?TP391 ????? ?A ???? ?1009-3044(2009)28-8023-03 Gender Classification Based on PCA and LBP LI Kun-lun, WANG Ming-yan (Department of Computer, Nanchang University, Nanchang 330031, China) Abstract: The regularity which amalgamated the characteristic of principal components erect (PCA) with local binary frame (LBP)s com bines the adva ntage in roving features of PCA with the advantage in Details of local texture of LBP and could blushing mushroom a picture better characteristics from face image for prevail vector appliance (SVM) to sexual urge classification.
Using Cascade method rather than traditional LBP method to ex tract LBP histogram characteristics of images and combine the features of LBP and PCA from extraction for SVM. The experimental results immortalise that the characteristics combined PCA with LBP has obvious advantages than the PCA and LBP singly in Gender identification. keystone words: texture; gender classification; principal c omponents synopsis; local binary pattern;su! pport vector machine ???????????????????????? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ??????????????????? ? ? 20 ?? 90 ?????? ? ????????????????????? ? ?? ? ? ? ? ? ? ? ? ? ? ? ? Adaboost ? ? ? ? ? ? ? ? 1991 ? ?Gollomb ? ? [1] ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? 30x30 ???????? ? ? 90 ??????????? 91.9% ? 1995 ? ?Brunelli ?? [2]??? HyperBF ?? ?...
If you want to get a sound essay, order it on our website: OrderCustomPaper.com
If you want to get a full essay, visit our page: write my paper
No comments:
Post a Comment