%0 Conference Proceedings
%T Shallow Neural Network Model for Hand-drawn Symbol Recognition in Multi-Writer Scenario
%A Sounak Dey
%A Anjan Dutta
%A Josep Llados
%A Alicia Fornes
%A Umapada Pal
%B 12th IAPR International Workshop on Graphics Recognition
%D 2017
%F Sounak Dey2017
%O DAG; 600.097; 600.121
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3057), last updated on Mon, 07 Dec 2020 14:30:00 +0100
%X One  of  the  main  challenges  in  hand  drawn  symbol recognition  is  the  variability  among  symbols  because  of  the different  writer  styles.  In  this  paper,  we  present  and  discuss some  results  recognizing  hand-drawn  symbols  with  a  shallow neural network. A neural network model inspired from the LeNet architecture has been used to achieve state-of-the-art results withvery less training data, which is very unlikely to the data hungry deep  neural  network.  From  the  results,  it  has  become  evident that  the  neural  network  architectures  can  efficiently  describe and  recognize  hand  drawn  symbols  from  different  writers  and can  model  the  inter  author  aberration
%U http://refbase.cvc.uab.es/files/DDL2017.pdf
%P 31-32