000126376 001__ 126376
000126376 005__ 20190617200602.0
000126376 02470 $$2ISI$$a000250382802035
000126376 037__ $$aCONF
000126376 245__ $$aFast Keypoint Recognition in Ten Lines of Code
000126376 269__ $$a2007
000126376 260__ $$bIEEE Xplore$$c2007
000126376 336__ $$aConference Papers
000126376 520__ $$aWhile feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a Naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust. Furthermore, it scales well to handle large number of classes. To recognize the patches surrounding keypoints, our classifier uses hundreds of simple binary features and models class posterior probabilities. We make the problem computationally tractable by assuming independence between arbitrary sets of features. Even though this is not strictly true, we demonstrate that our classifier nevertheless performs remarkably well on image datasets containing very significant perspective changes.
000126376 6531_ $$acomputer vision
000126376 6531_ $$akeypoint recognition
000126376 6531_ $$anaive Bayesian
000126376 6531_ $$aobject detection
000126376 6531_ $$aimage classification
000126376 700__ $$aOzuysal, Mustafa
000126376 700__ $$0240252$$g112366$$aFua, Pascal
000126376 700__ $$0240235$$g149007$$aLepetit, Vincent
000126376 7112_ $$dJune 18-23, 2007$$cMinneapolis$$aIEEE Conference on Computer Vision and Pattern Recognition
000126376 8564_ $$uhttp://cvpr.cv.ri.cmu.edu$$zURL
000126376 8564_ $$uhttps://infoscience.epfl.ch/record/126376/files/OzuysalFL07.pdf$$zn/a$$s3526888
000126376 909C0 $$xU10659$$0252087$$pCVLAB
000126376 909CO $$ooai:infoscience.tind.io:126376$$qGLOBAL_SET$$pconf$$pIC
000126376 937__ $$aCVLAB-CONF-2008-004
000126376 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000126376 980__ $$aCONF