PT Journal
AU Thanh Ha Do
   Salvatore Tabbone
   Oriol Ramos Terrades
TI Sparse representation over learned dictionary for symbol recognition
SO Signal Processing
JI SP
PY 2016
BP 36
EP 47
VL 125
DE Symbol Recognition; Sparse Representation; Learned Dictionary; Shape Context; Interest Points
AB 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.
ER