Transfer Learning of Mixture Texture Models

0535433 20250123090435.920201202235959.9 85097519102 001351026500065 10.1007/978-3-030-63007-2_65 Transfer Learning of Mixture Texture Models 13 s. P cav_un_epca*0535432978-3-030-63006-50302-9743Computational Collective Intelligence825-837ChamSpringer Nature Switzerland AG2020NguyenN. T.HoangB. H.HuynhC. P.HwangD.TrawinskiB.VossenG. Texture modeling transfer learning compound random field model bidirectional texture function cav_un_auth*0101093 Haindl Michal UTIA-B Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101100 Havlíček Vojtěch UTIA-B Rozpoznávání obrazu Department of Pattern Recognition RO RO Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2020/RO/haindl-0535433.pdf GA19-12340S GA ČR CZ cav_un_auth*0376011 A transfer learning approach for multidimensional parametric mixture random field-based textural representation is introduced. The proposed transfer learning approach allows alleviating the multidimensional mixture models requirement for sufficiently large, but not always available, learning data sets. These compound random field models consist of an underlying structure model that controls transitions between several sub-models, each of them has different characteristics. The structure model proposed is a two-dimensional probabilistic mixture model, either of the Bernoulli or Gaussian mixture type. Local textures are modeled using the fully multispectral three-dimensional Gaussian mixture sub-models. Both presented compound random field models allow the reproduction of, compresses, edits, and enlarges a given measured color, multispectral, or bidirectional texture function (BTF) texture so that ideally, both measured and synthetic textures are visually indiscernible. cav_un_auth*0400273 International Conference on Computational Collective Intelligence 2020 /12./ 20201130 20201203 Da Nang VN BD 20000 20200 20205 2021 2 PR RVO:67985556 http://hdl.handle.net/11104/0314144 S 2020 85097519102 SCOPUS PUBMED 001351026500065 WOS cav_un_epca*0535432 Computational Collective Intelligence 978-3-030-63006-5 0302-9743 1611-3349 825 837 Cham Springer Nature Switzerland AG 2020 Lecture Notes in Artificial Intelligence 12496 340 Nguyen N. T. 340 Hoang B. H. 340 Huynh C. P. 340 Hwang D. 340 Trawinski B. 340 Vossen G.