%0 Journal Article
%T Sparse representation over learned dictionary for symbol recognition
%A Thanh Ha Do
%A Salvatore Tabbone
%A Oriol Ramos Terrades
%J Signal Processing
%D 2016
%V 125
%F Thanh Ha Do2016
%O DAG; 600.061; 600.077
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2946), last updated on Thu, 07 Mar 2019 11:04:29 +0100
%X In this paper we propose an original sparse vector model for symbol retrieval task. More specically, we apply the K-SVD algorithm for learning a visual dictionary based on symbol descriptors locally computed around interest points. Results on benchmark datasets show that the obtained sparse representation is competitive related to state-of-the-art methods. Moreover, our sparse representation is invariant to rotation and scale transforms and also robust to degraded images and distorted symbols. Thereby, the learned visual dictionary is able to represent instances of unseen classes of symbols.
%K Symbol Recognition
%K Sparse Representation
%K Learned Dictionary
%K Shape Context
%K Interest Points
%U https://doi.org/10.1016/j.sigpro.2015.12.020
%U http://refbase.cvc.uab.es/files/DTR2016.pdf
%P 36-47