Aslan S.Akgul C.B.Sankur B.Tunalı, Turhan2023-06-162023-06-1620169.78E+12https://doi.org/10.1109/SIU.2016.7496181https://hdl.handle.net/20.500.14365/360024th Signal Processing and Communication Application Conference, SIU 2016 -- 16 May 2016 through 19 May 2016 -- 122605We designed SymPaD framework, a model-driven visual dictionary construction and description method, with new shape models and quantized shape library. We demonstrate that, with this new design, the most current model-driven dictionary construction method is outperformed with even smaller dictionary in object recognition and image retrieval tasks. © 2016 IEEE.trinfo:eu-repo/semantics/closedAccessdescriptorimage understandingmodel-driven visual dictionaryImage understandingObject recognitionCurrent modelingDescription methodDescriptorsDictionary constructionsModel-drivenShape modelVisual dictionariesSignal processingConference Object10.1109/SIU.2016.74961812-s2.0-84982806337