. "16501" . "\u0160ulc, Milan" . "Praha" . "2"^^ . "20"^^ . "Computer Vision; Texture; Classification; LBP; LBP-HF; Histogram; SVM; Feature maps; Ffirst"@en . . "Fast Features Invariant to Rotation and Scale of Texture" . . "Matas, Ji\u0159\u00ED" . . . "RIV/68407700:21230/14:00218863!RIV15-MSM-21230___" . . . "http://cmp.felk.cvut.cz/~sulcmila/papers/Sulc-TR-2014-12.pdf" . "Fast Features Invariant to Rotation and Scale of Texture"@en . . . . . . "Fast Features Invariant to Rotation and Scale of Texture" . "RIV/68407700:21230/14:00218863" . . . "A family of novel texture representations called Ffirst, the Fast Features Invariant to Rotation and Scale of Texture, is introduced. New rotation invariants are proposed, extending the LBP-HF features, improving the recognition accuracy. Using the full set of LBP features, as opposed to uniform only, leads to further improvement. Linear Support Vector Machines with an approximate $chi^2$-kernel map are used for fast and precise classification. Experimental results show that Ffirst exceeds the best reported results in texture classification on three difficult texture datasets KTH-TIPS2a, KTH-TIPS2b and ALOT, achieving 88%, 76% and 96% accuracy respectively. The recognition rates are above 99% on standard texture datasets KTH-TIPS, Brodatz32, UIUCTex, UMD, CUReT." . . "P(GBP103/12/G084), S" . . "Fast Features Invariant to Rotation and Scale of Texture"@en . "Center for Machine Perception, K13133 FEE Czech Technical University" . . . . . "A family of novel texture representations called Ffirst, the Fast Features Invariant to Rotation and Scale of Texture, is introduced. New rotation invariants are proposed, extending the LBP-HF features, improving the recognition accuracy. Using the full set of LBP features, as opposed to uniform only, leads to further improvement. Linear Support Vector Machines with an approximate $chi^2$-kernel map are used for fast and precise classification. Experimental results show that Ffirst exceeds the best reported results in texture classification on three difficult texture datasets KTH-TIPS2a, KTH-TIPS2b and ALOT, achieving 88%, 76% and 96% accuracy respectively. The recognition rates are above 99% on standard texture datasets KTH-TIPS, Brodatz32, UIUCTex, UMD, CUReT."@en . . "21230" . . "[4EF75539193F]" . "2"^^ . .